Publish Sign in

Self-Review Agent Skill

Pre-submission self-review for the user's own manuscripts, applying a reviewer perspective.

Install this skill Read the source first Free Written by Aperivue
Context cost
126.6k tokensestimated from the bundle, loaded when it triggers
Bundle
200 of 344 fileshanded out here; the rest is at its source
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Use when checking your own manuscript before submission from a reviewer's perspective. Returns anticipated Major/Minor comments with fixes, including numerical, citation and leakage checks, with an optional multi-reviewer panel. Someone else's paper is /peer-review.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivity
Filed under

Productivity & Workflow

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md48.3 kB · preview
--- name: self-review metadata: triggers: "self-review, pre-submission check, check my paper, reviewer perspective, manuscript self-check" ---
8# Self-Review Skill
9
10Check the user's own manuscript before submission and produce an actionable list of anticipated
11reviewer comments, each with a specific fix — not a written review.
12
13## Optional Flags
14
15- --fix: after the report, apply fixes for every issue with fixable_by_ai: true, editing the manuscript in place, then report a diff summary. Never fix fixable_by_ai: false issues (missing data, design flaws). Maximum 2 fix-and-re-review iterations; if the score is still below threshold after the second, stop and report what remains as structural (inside /write-paper this routes to Phase 7.4a Audit Recovery).
16- --json: also emit the structured JSON block (Phase 3c). Default when called from /write-paper Phase 7.
17- --panel: run the multi-agent panel review (Phase 2.6) — domain-expert reviewers in parallel plus an editor synthesis — instead of the single-pass review. Opt-in and **off by default**, because it spawns N reviewer agents + 1 editor and costs several times more tokens; reserve it for a high-stakes final pass on a top-tier target. Do **not** combine with --fix: a panel diagnoses and prioritizes; run --fix as a separate pass once the author has triaged the panel's findings.
18
19## Severity Framing
20
21- **Fatal**: a design flaw existing data cannot fix (data leakage that invalidates all results, no reference standard, label–feature circularity). Submission would likely be rejected. Reserve Fatal for true design-level problems.
22- **Fixable**: significant but addressable with existing data (missing calibration, unclear exclusion criteria, absent CIs, incomplete reporting). Most issues are Fixable.
23
24## Two Objectives: the Floor and the Ceiling
25
26The **floor** (categories A–K and the gates of Phases 2.5–2.5f) minimizes rejection-for-cause —
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md6,440 words
Files200
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈110
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
126,515
on trigger
The instruction body and 199 supporting files, read only when the skill fires.
63.3%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

126.6k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

The download carries 200 of the 344 files in its source folder; the list here names 200 files, 1173.8 kB on disk. Mostly text — the instructions the model reads — with 77 scripts in it that your client would run only if the instructions tell it to. The other 144 are not in the download — the first 100 are listed after these, with why.

  • SKILL.md48.3 kB
  • skill.yml5.6 kB
  • references/panel_review_template.md17.0 kB
  • scripts/_frontmatter.py2.4 kB
  • scripts/_prose.py2.5 kB
  • scripts/_qc_findings.py6.4 kB
  • scripts/check_analysis_definitions.py13.0 kB
  • scripts/check_aphorism_density.py8.4 kB
  • scripts/check_artifact_coverage.py17.2 kB
  • scripts/check_baseline_drift.py11.2 kB
  • scripts/check_binning_consistency.py20.3 kB
  • scripts/check_citation_order.py22.8 kB
  • scripts/check_claim_artifact.py35.4 kB
  • scripts/check_classical_style.py17.3 kB
  • scripts/check_cohort_arithmetic.py39.3 kB
  • scripts/check_confounding_completeness.py25.3 kB
  • scripts/check_cv_leakage.py6.4 kB
  • scripts/check_dta_denominators.py7.8 kB
  • scripts/check_editorial_impression.py22.3 kB
  • scripts/check_effect_stability.py10.6 kB
  • scripts/check_emphasis_density.py6.7 kB
  • scripts/check_figure_citation.py12.9 kB
  • scripts/check_incorporation_bias.py8.8 kB
  • scripts/check_nested_group_comparison.py6.4 kB
  • scripts/check_null_calibration.py8.6 kB
  • scripts/check_paired_difference_estimator.py6.7 kB
  • scripts/check_panel_diversity.py26.0 kB
  • scripts/check_paren_spans.py6.5 kB
  • scripts/check_perspective_structure.py12.1 kB
  • scripts/check_reference_adequacy.py17.8 kB
  • scripts/check_reported_p_from_counts.py22.1 kB
  • scripts/check_reviewer_team_consistency.py15.5 kB
  • scripts/check_rhetorical_density.py11.0 kB
  • scripts/check_rounded_delta.py7.1 kB
  • scripts/check_scope_coherence.py21.6 kB
  • scripts/check_supplement_hygiene.py18.2 kB
  • scripts/check_table_percentages.py13.9 kB
  • scripts/refinement_regression.py9.0 kB
  • scripts/refinement_stop.py11.7 kB
  • tests/test_aphorism_density.sh2.5 kB
  • tests/test_artifact_coverage.sh3.0 kB
  • tests/test_binning_consistency.sh3.8 kB
  • tests/test_citation_order.sh6.9 kB
  • tests/test_claim_artifact.sh7.2 kB
  • tests/test_classical_style.sh4.2 kB
  • tests/test_cohort_arithmetic.sh7.9 kB
  • tests/test_confounding_completeness.sh9.7 kB
  • tests/test_cv_leakage.sh1.5 kB
  • tests/test_editorial_impression.sh4.0 kB
  • tests/test_emphasis_density.sh1.3 kB
  • tests/test_figure_citation.sh3.4 kB
  • tests/test_figure_citation_labels.sh4.7 kB
  • tests/test_null_calibration.sh2.5 kB
  • tests/test_panel_diversity.sh7.6 kB
  • tests/test_panel_mode.sh3.7 kB
  • tests/test_paren_spans.sh1.8 kB
  • tests/test_qc_severity_vocabulary.sh4.1 kB
  • tests/test_reference_adequacy.sh3.9 kB
  • tests/test_reviewer_team_consistency.sh5.5 kB
  • tests/test_rhetorical_density.sh2.9 kB
  • tests/test_rounded_delta.sh1.5 kB
  • tests/test_scope_coherence.sh6.8 kB
  • tests/test_supplement_hygiene.sh5.3 kB
  • tests/test_table_percent_denominator.sh4.3 kB
  • references/domain-probes/ai_overclaiming.md15.8 kB
  • references/domain-probes/case_report.md9.1 kB
  • references/domain-probes/clinical_prediction_model.md7.9 kB
  • references/domain-probes/diagnostic_accuracy.md14.9 kB
  • references/domain-probes/equity_fairness.md7.7 kB
  • references/domain-probes/health_economic_evaluation.md8.4 kB
  • references/domain-probes/image_synthesis.md6.3 kB
  • references/domain-probes/mendelian_randomization.md11.2 kB
  • references/domain-probes/mllm_evaluation.md7.8 kB
  • references/domain-probes/model_development.md15.8 kB
  • references/domain-probes/narrative_review.md13.0 kB
  • references/domain-probes/network_meta_analysis.md9.5 kB
  • references/domain-probes/observational_confounding.md36.7 kB
  • references/domain-probes/polygenic_risk_score.md9.7 kB
  • references/domain-probes/qualitative_research.md7.0 kB
  • references/domain-probes/radiomics.md5.8 kB
  • references/domain-probes/rct_trial.md9.3 kB
  • references/domain-probes/record_routinely_collected_data.md7.6 kB
  • references/domain-probes/scoping_review.md7.2 kB
  • references/domain-probes/self_improving_system.md8.4 kB
  • references/domain-probes/sr_ma.md20.1 kB
  • references/domain-probes/survey_research.md7.2 kB
  • references/domain-probes/survival_prognostic.md14.7 kB
  • references/exemplar_findings/cohort_arithmetic_mismatch.md1.8 kB
  • references/exemplar_findings/cross_sectional_mediation.md2.8 kB
  • references/exemplar_findings/estimand_drift_posthoc_primary.md2.2 kB
  • references/exemplar_findings/over_adjustment_collider.md2.7 kB
  • references/exemplar_findings/prediction_two_null_conflation.md2.7 kB
  • references/exemplar_findings/README.md3.1 kB
  • references/exemplar_findings/scope_overreach_cross_sectional.md1.9 kB
  • references/exemplar_findings/unadjusted_confounder.md2.0 kB
  • references/phases/confounding_completeness.md5.3 kB
  • references/phases/phase2_5a_source_fidelity.md6.0 kB
  • references/phases/phase2_5a2_design_power.md4.3 kB
  • references/phases/phase2_5b_screening_counts.md7.7 kB
  • references/phases/phase2_5c_reference_scans.md7.9 kB
  • references/phases/phase2_5d_xref_qc.md5.6 kB
  • references/phases/phase2_5f_claim_artifact.md12.5 kB
  • references/phases/phase2_6_panel.md10.4 kB
  • references/phases/phase2_systematic_check.md20.4 kB
  • references/phases/phase3c_json_output.md6.7 kB
  • references/phases/phase4_fix_support.md3.4 kB
  • scripts/check_analysis_definitions_challenge/problem.md2.7 kB
  • scripts/check_analysis_definitions_challenge/verify.sh1.6 kB
  • scripts/check_baseline_drift_challenge/problem.md2.4 kB
  • scripts/check_baseline_drift_challenge/verify.sh2.2 kB
  • scripts/check_dta_denominators_challenge/problem.md1.6 kB
  • scripts/check_dta_denominators_challenge/verify.sh1.4 kB
  • scripts/check_effect_stability_challenge/problem.md1.0 kB
  • scripts/check_effect_stability_challenge/verify.sh2.1 kB
  • scripts/check_figure_citation_challenge/problem.md1.4 kB
  • scripts/check_figure_citation_challenge/verify.sh1.6 kB
  • scripts/check_incorporation_bias_challenge/problem.md0.9 kB
  • scripts/check_incorporation_bias_challenge/verify.sh1.8 kB
  • scripts/check_nested_group_comparison_challenge/problem.md1.5 kB
  • scripts/check_nested_group_comparison_challenge/verify.sh1.5 kB
  • scripts/check_paired_difference_estimator_challenge/problem.md1.5 kB
  • scripts/check_paired_difference_estimator_challenge/verify.sh1.5 kB
  • scripts/check_perspective_structure_challenge/problem.md2.5 kB
  • scripts/check_perspective_structure_challenge/verify.sh3.4 kB
  • scripts/check_reported_p_from_counts_challenge/problem.md1.6 kB
  • scripts/check_reported_p_from_counts_challenge/verify.sh1.5 kB
  • scripts/check_table_percentages_challenge/problem.md3.2 kB
  • scripts/check_table_percentages_challenge/verify.sh4.2 kB
  • scripts/cohort_arith_binding_challenge/verify.sh5.3 kB
  • scripts/confounding_findings_challenge/verify.sh5.1 kB
  • scripts/disclosure_placement_challenge/verify.sh6.4 kB
  • scripts/refinement_regression_challenge/problem.md2.4 kB
  • scripts/refinement_regression_challenge/verify.sh3.1 kB
  • scripts/refinement_stop_challenge/problem.md3.0 kB
  • scripts/refinement_stop_challenge/verify.sh3.4 kB
  • tests/fixtures/aphorism_clean.md3.4 kB
  • tests/fixtures/aphorism_dense.md1.7 kB
  • tests/fixtures/aphorism_frontmatter.md1.1 kB
  • tests/fixtures/citation_order_bad.md0.7 kB
  • tests/fixtures/citation_order_frontmatter.md0.9 kB
  • tests/fixtures/citation_order_good.md0.9 kB
  • tests/fixtures/citation_order_ref_gap.md0.5 kB
  • tests/fixtures/citation_order_ref_good.md0.4 kB
  • tests/fixtures/citation_order_ref_order_bad.md0.7 kB
  • tests/fixtures/citation_order_ref_range_ok.md1.0 kB
  • tests/fixtures/citation_order_section_bad.md0.2 kB
  • tests/fixtures/citation_order_section_good.md0.3 kB
  • tests/fixtures/citation_order_uncited.md0.6 kB
  • tests/fixtures/claim_body_reassign.md0.1 kB
  • tests/fixtures/claim_frontmatter_changelog.md0.5 kB
  • tests/fixtures/claim_manuscript.md0.7 kB
  • tests/fixtures/claim_manuscript_single_primary.md0.2 kB
  • tests/fixtures/claim_manuscript_structured.md0.2 kB
  • tests/fixtures/claim_prereg.md0.3 kB
  • tests/fixtures/claim_prereg_structured.md0.3 kB
  • tests/fixtures/claim_registration_bad.md0.2 kB
  • tests/fixtures/claim_registration_clean.md0.6 kB
  • tests/fixtures/classical_metadoc.md0.4 kB
  • tests/fixtures/cohort_bad.md0.5 kB
  • tests/fixtures/cohort_clean.md0.5 kB
  • tests/fixtures/cohort_dup_ci.md0.3 kB
  • tests/fixtures/cohort_dup_ci_clean.md0.3 kB
  • tests/fixtures/cohort_followup_criterion.md0.1 kB
  • tests/fixtures/cohort_followup_ok.md0.2 kB
  • tests/fixtures/cohort_nested_models.md0.3 kB
  • tests/fixtures/cohort_nested_models_base.md0.2 kB
  • tests/fixtures/cohort_partition.csv0.1 kB
  • tests/fixtures/cohort_partition_prose.md0.4 kB
  • tests/fixtures/cohort_partition_prose_clean.md0.9 kB
  • tests/fixtures/cohort_rate_tier_fp.md0.2 kB
  • tests/fixtures/cohort_repeat_subjects.csv0.1 kB
  • tests/fixtures/cohort_unit_disclosed.md0.6 kB
  • tests/fixtures/cohort_unit_undisclosed.md0.4 kB
  • tests/fixtures/coverage_clean.md0.5 kB
  • tests/fixtures/coverage_manuscript.md0.3 kB
  • tests/fixtures/coverage_promised_stat.md0.3 kB
  • tests/fixtures/coverage_promised_stat_ok.md0.2 kB
  • tests/fixtures/cv_leakage_bad.md0.2 kB
  • tests/fixtures/cv_leakage_clean.md0.2 kB
  • tests/fixtures/editorial_clean.md2.7 kB
  • tests/fixtures/editorial_defensive.md2.5 kB
  • tests/fixtures/emphasis_clean.md0.5 kB
  • tests/fixtures/emphasis_overuse.md0.4 kB
  • tests/fixtures/figcite_credit_bad.md0.3 kB
  • tests/fixtures/figcite_credit_ok.md0.3 kB
  • tests/fixtures/figcite_embedded.md0.3 kB
  • tests/fixtures/figcite_not_embedded.md0.2 kB
  • tests/fixtures/figure_clean.md0.4 kB
  • tests/fixtures/figure_orphan.md0.3 kB
  • tests/fixtures/null_bad.md0.4 kB
  • tests/fixtures/null_clean.md0.5 kB
  • tests/fixtures/null_region_masked.md0.6 kB
  • tests/fixtures/panel_collapse.json0.9 kB
  • tests/fixtures/panel_good.json1.6 kB
  • tests/fixtures/panel_monoculture.json1.3 kB
  • tests/fixtures/panel_one_returned.json0.4 kB
  • tests/fixtures/panel_stats_lens.json1.4 kB
  • tests/fixtures/paren_clean.md0.3 kB
  • tests/fixtures/paren_corrupt.md0.6 kB
  • tests/fixtures/refadeq_letter.md0.8 kB

Not in the download

The first 100 are named here, those the skill reads first. Over the limit is past 200 files or 4 MB a skill. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take them from its source.

  • tests/fixtures/refadeq_original_fixed.mdread · over the limit
  • tests/fixtures/refadeq_original_uncited.mdread · over the limit
  • tests/fixtures/rhetorical_clean.mdread · over the limit
  • tests/fixtures/rhetorical_dense.mdread · over the limit
  • tests/fixtures/roster_3.jsonread · over the limit
  • tests/fixtures/roster_4.jsonread · over the limit
  • tests/fixtures/roster_indep_substrate.jsonread · over the limit
  • tests/fixtures/roster_mono_substrate.jsonread · over the limit
  • tests/fixtures/rounded_delta_bad.mdread · over the limit
  • tests/fixtures/rounded_delta_clean.mdread · over the limit
  • tests/fixtures/scope_antipattern_list.mdread · over the limit
  • tests/fixtures/scope_bad.mdread · over the limit
  • tests/fixtures/scope_clean.mdread · over the limit
  • tests/fixtures/scope_disclaimer.mdread · over the limit
  • tests/fixtures/scope_gradient.mdread · over the limit
  • tests/fixtures/scope_gradient_tested.mdread · over the limit
  • tests/fixtures/scope_metadoc.mdread · over the limit
  • tests/fixtures/scope_surrogate.mdread · over the limit
  • tests/fixtures/scope_universal_negative.mdread · over the limit
  • tests/fixtures/scope_universal_negative_ok.mdread · over the limit
  • tests/fixtures/scope_yield.mdread · over the limit
  • tests/fixtures/scope_yield_defined.mdread · over the limit
  • tests/fixtures/style_bad.mdread · over the limit
  • tests/fixtures/style_clean.mdread · over the limit
  • tests/fixtures/style_dagger_footnote.mdread · over the limit
  • tests/fixtures/style_emdash_structural.mdread · over the limit
  • tests/fixtures/supp_clean.mdread · over the limit
  • tests/fixtures/supp_dirty.mdread · over the limit
  • tests/fixtures/supp_xref_body.mdread · over the limit
  • tests/fixtures/supp_xref_supp.mdread · over the limit
  • tests/fixtures/supplement_pii_clean.mdread · over the limit
  • tests/fixtures/supplement_pii_tie.mdread · over the limit
  • tests/fixtures/table1_by_exposure.csvread · over the limit
  • tests/fixtures/table1_by_exposure_dbcodes.csvread · over the limit
  • tests/fixtures/table1_meansd_wide.csvread · over the limit
  • scripts/check_analysis_definitions_challenge/expected/defined.txtread · over the limit
  • scripts/check_analysis_definitions_challenge/expected/undefined.txtread · over the limit
  • scripts/check_analysis_definitions_challenge/fixture/defined.mdread · over the limit
  • scripts/check_analysis_definitions_challenge/fixture/undefined.mdread · over the limit
  • scripts/check_baseline_drift_challenge/fixture/baseline.mdread · over the limit
  • scripts/check_baseline_drift_challenge/fixture/drifted.mdread · over the limit
  • scripts/check_baseline_drift_challenge/fixture/overhedged.mdread · over the limit
  • scripts/check_baseline_drift_challenge/fixture/stable.mdread · over the limit
  • scripts/check_dta_denominators_challenge/expected/bad.txtread · over the limit
  • scripts/check_dta_denominators_challenge/expected/ok.txtread · over the limit
  • scripts/check_dta_denominators_challenge/fixture/dta_bad.mdread · over the limit
  • scripts/check_dta_denominators_challenge/fixture/dta_ok.mdread · over the limit
  • scripts/check_effect_stability_challenge/expected/bad.txtread · over the limit
  • scripts/check_effect_stability_challenge/expected/ok.txtread · over the limit
  • scripts/check_effect_stability_challenge/fixture/effect_bad.mdread · over the limit
  • scripts/check_effect_stability_challenge/fixture/effect_ok.mdread · over the limit
  • scripts/check_figure_citation_challenge/fixture/panel_regression.mdread · over the limit
  • scripts/check_figure_citation_challenge/fixture/real_orphan.mdread · over the limit
  • scripts/check_incorporation_bias_challenge/expected/bad.txtread · over the limit
  • scripts/check_incorporation_bias_challenge/expected/ok.txtread · over the limit
  • scripts/check_incorporation_bias_challenge/fixture/incorp_bad.mdread · over the limit
  • scripts/check_incorporation_bias_challenge/fixture/incorp_ok.mdread · over the limit
  • scripts/check_nested_group_comparison_challenge/expected/clean.txtread · over the limit
  • scripts/check_nested_group_comparison_challenge/expected/nested.txtread · over the limit
  • scripts/check_nested_group_comparison_challenge/fixture/clean.mdread · over the limit
  • scripts/check_nested_group_comparison_challenge/fixture/nested.mdread · over the limit
  • scripts/check_paired_difference_estimator_challenge/expected/bad.txtread · over the limit
  • scripts/check_paired_difference_estimator_challenge/expected/ok.txtread · over the limit
  • scripts/check_paired_difference_estimator_challenge/fixture/paired_bad.mdread · over the limit
  • scripts/check_paired_difference_estimator_challenge/fixture/paired_ok.mdread · over the limit
  • scripts/check_perspective_structure_challenge/fixture/edge_hardened.mdread · over the limit
  • scripts/check_perspective_structure_challenge/fixture/not_perspective.mdread · over the limit
  • scripts/check_perspective_structure_challenge/fixture/perspective_bad.mdread · over the limit
  • scripts/check_perspective_structure_challenge/fixture/perspective_ok.mdread · over the limit
  • scripts/check_reported_p_from_counts_challenge/expected/bad.txtread · over the limit
  • scripts/check_reported_p_from_counts_challenge/expected/ok.txtread · over the limit
  • scripts/check_reported_p_from_counts_challenge/fixture/p_bad.mdread · over the limit
  • scripts/check_reported_p_from_counts_challenge/fixture/p_ok.mdread · over the limit
  • scripts/check_table_percentages_challenge/expected/bad.txtread · over the limit
  • scripts/check_table_percentages_challenge/expected/ok.txtread · over the limit
  • scripts/check_table_percentages_challenge/fixture/table_bad.mdread · over the limit
  • scripts/check_table_percentages_challenge/fixture/table_ok.mdread · over the limit
  • scripts/cohort_arith_binding_challenge/fixture/decimal_person_time.mdread · over the limit
  • scripts/cohort_arith_binding_challenge/fixture/genuine_defects.mdread · over the limit
  • scripts/confounding_findings_challenge/fixture/adjusted.txtread · over the limit
  • scripts/confounding_findings_challenge/fixture/defining.txtread · over the limit
  • scripts/confounding_findings_challenge/fixture/table1.csvread · over the limit
  • scripts/disclosure_placement_challenge/fixture/about_disclosure.mdread · over the limit
  • scripts/disclosure_placement_challenge/fixture/manuscript.mdread · over the limit
  • scripts/refinement_regression_challenge/fixture/churning/ledger.jsonlread · over the limit
  • scripts/refinement_regression_challenge/fixture/converged/ledger.jsonlread · over the limit
  • scripts/refinement_regression_challenge/fixture/findings_regression/ledger.jsonlread · over the limit
  • scripts/refinement_regression_challenge/fixture/firstrun/ledger.jsonlread · over the limit
  • scripts/refinement_regression_challenge/fixture/progressing/ledger.jsonlread · over the limit
  • scripts/refinement_regression_challenge/fixture/regression/ledger.jsonlread · over the limit
  • scripts/refinement_stop_challenge/fixture/continue/cohort_arithmetic.jsonread · over the limit
  • scripts/refinement_stop_challenge/fixture/continue/editorial_impression.jsonread · over the limit
  • scripts/refinement_stop_challenge/fixture/findings_major/editorial_impression.jsonread · over the limit
  • scripts/refinement_stop_challenge/fixture/minor_optional/cohort_arithmetic.jsonread · over the limit
  • scripts/refinement_stop_challenge/fixture/minor_optional/editorial_impression.jsonread · over the limit
  • scripts/refinement_stop_challenge/fixture/overhardening/cohort_arithmetic.jsonread · over the limit
  • scripts/refinement_stop_challenge/fixture/overhardening/editorial_impression.jsonread · over the limit
  • scripts/refinement_stop_challenge/fixture/zero_edit/cohort_arithmetic.jsonread · over the limit
  • scripts/refinement_stop_challenge/fixture/zero_edit/editorial_impression.jsonread · over the limit
  • scripts/refinement_regression_challenge/fixture/churning/qc/gate.jsonread · over the limit
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 77 scripts beside the text, so the download is 200 files — not the whole of its source: at least 144 files are left out, and the skill reads 100 of them. The first 100 are listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Self-Review · 126.6k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/aperivue-self-review/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/self-review" ] && { [ ! -e .claude/skills/self-review ] || { mv .claude/skills/self-review "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/self-review" .claude/skills/ && echo "Installed .claude/skills/self-review"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add aperivue/self-review

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/self-review/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/aperivue-self-review/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/self-review" ] && { [ ! -e ~/.claude/skills/self-review ] || { mv ~/.claude/skills/self-review "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/self-review" ~/.claude/skills/ && echo "Installed ~/.claude/skills/self-review" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/self-review/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. Not in this download: at least 144 files of its source, 100 of them read by its SKILL.md or scripts (the list, and why). Take them from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceaperivue/self-review

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

AP
Aperivue

Publishes on mcprush.

0 servers listed59 skills listednot claimed
Profile
Publisher
Servers0
Claim this skill