claude-skill
starsforks
How to install claude-skill?
cmertdalli/polisci-review/claude-skill
$npx -y skills add cmertdalli/polisci-review --skill claude-skillRun a public-facing political science pre-submission audit with journal personas, stage gating, and evidence-grounded issue reporting
SKILL.md
| 1 | You are coordinating a rigorous political science pre-submission audit. |
| 2 | |
| 3 | This installed skill is self-contained. Read the canonical review files in this directory before reviewing: |
| 4 | |
| 5 | 1. `./core/invocation-spec.md` |
| 6 | 2. `./core/journal-manifest.json` |
| 7 | 3. `./core/paper-discovery.md` |
| 8 | 4. `./core/track-stage-rules.md` |
| 9 | 5. `./core/issue-taxonomy.md` |
| 10 | 6. `./core/references/guardrails.md` |
| 11 | 7. `./core/references/journal-signals.md` |
| 12 | 8. `./core/references/journal-personas.md` |
| 13 | 9. the relevant module specs in `./core/modules/` |
| 14 | 10. `./core/report-template.md` |
| 15 | |
| 16 | Then: |
| 17 | |
| 18 | 1. Parse `$ARGUMENTS` using the canonical invocation contract. |
| 19 | 2. Discover the manuscript and any linked `.tex`, appendix, figure, table, and bibliography files. Prefer `.tex` whenever available; support `.docx`, `.md`, `.txt`, and text-readable `.pdf` on a best-effort basis. |
| 20 | 3. Detect the stage and track if they were omitted. |
| 21 | 4. Run the 9-module review structure defined in `./core/modules/`. |
| 22 | 5. Write two output files in the main manuscript directory when a manuscript path is available; otherwise write them in the current working directory: |
| 23 | - `review-report.md` using the canonical report template |
| 24 | - `review-report.json` conforming to `./core/issue-schema.json` |
| 25 | 6. Before finishing, make sure `review-report.json` is valid JSON and briefly confirm the paths you wrote. |
| 26 | |
| 27 | Mandatory guardrails: |
| 28 | |
| 29 | - Do not merely describe the outputs. Write the files unless the environment prevents file output. |
| 30 | - If the environment cannot write files, say so explicitly and return the Markdown report plus the JSON artifact directly in the response. |
| 31 | - Every issue must include a `module`, location anchor, evidence status, and `journal_policy_ref`. |
| 32 | - Do not claim missing references, broken cross-references, or absent robustness checks without checking the files. |
| 33 | - If `.docx` or `.pdf` text cannot be read reliably, say so and ask for exported text instead of guessing. |
| 34 | - Proposals and dissertations must be reviewed with stage-aware expectations. |
| 35 | - Use `PA` for `Political Analysis`. |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
