Catalog
affaan-m/ecc-contribution-review

affaan-m

ecc-contribution-review

Prepare an ECC skill contribution for review by organizing repository, install-surface, cross-harness, validation, security, and commit observations into a local proposal. Use when preparing a skill contribution for review.

v1.0LATEST
NewUpdated Nov 17, 2026

ECC Skill Contribution Review Packet

Use this workflow to prepare skill contribution observations for maintainer review. This version supports changeKind: "skill" with canonical source under skills/. It compiles supplied observations; it does not independently inspect Git, files, CI, test results, coverage, or referenced evidence. Treat every imported claim as unverified until a reviewer checks its evidence.

Workflow

  1. Start from the active ECC checkout. Record the branch, base and head, package lock, install manifests, catalog generator, skill placement policy, and a checkpoint.

  2. Identify the canonical source under skills/ for curated workflows. Keep generated, learned, and imported content outside shipped sources.

  3. Record the change intent, artifact graph, install coverage, harness copies, catalog and registry counts, test phases, coverage, security review, budgets, and commit proposal with evidence references.

  4. Run the required validators and tests separately. Record exact commands, results, and evidence. The compiler does not execute them.

  5. Copy the template, then edit the copy to replace every placeholder with current observations and references to evidence you gathered. The template is intentionally incomplete and must not be treated as an observation. After editing it, compile the packet:

    mkdir -p .memory-kit
    cp skills/ecc-contribution-review/templates/contribution-review-observation.json \
      .memory-kit/contribution-review-observation.json
    python3 skills/ecc-contribution-review/scripts/compile_contribution_review.py \
      .memory-kit/contribution-review-observation.json \
      --output .memory-kit/ecc-contribution-review.json
    

    --output writes a new capsule file in the existing parent directory and refuses to overwrite any existing path. The compiler does not create directories, modify source files, run tests, update catalogs, commit, push, or open a pull request. Exit code 0 means a packet was emitted without reported faults or contradictions; review is still required. Exit code 2 means validation faults, contradictions, or an input/output error. A diagnostic packet may still be emitted with exit code 2. Inspect the packet and stderr; the exit code alone does not establish whether output exists.

  6. Review every reported contradiction and semantic page fault. The compiler returns require_review for structurally valid input and never approves a contribution. It does not prove that supplied claims are true or CI passed.

  7. Recompile after changes to HEAD, policy, manifests, catalog, adapters, tests, coverage, security findings, or review evidence.

Local Contract

The packet describes source ownership, generated-root exclusion, install coverage, normalized harness identity, catalog reconciliation, TDD claims, security review, validation gates, and a conventional-commit proposal. Runner proposals are typed argument arrays and remain unexecuted. All generated authority and external effects remain false.

See the workflow, the design, and the contract. The JSON input is an illustrative fixture, not a current repository observation.

Files20
20 files · 109.3 KB

Select a file to preview

Overall Score

88/100

Grade

A

Excellent

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

92

Quality

85

Clarity

84

Completeness

88

Summary

This skill guides users through preparing ECC (Everything Claude Code) skill contributions for review by compiling structured observation data into a JSON review packet. The workflow validates that observations are internally consistent with the ECC skill contribution contract, records repository state, artifact hashes, test coverage, security findings, and validation gates without executing tests or modifying files. It is a data-validation and packet-compilation tool, not a CI runner.

Detected Capabilities

file read (JSON observation input)file write (JSON capsule output to new paths only)JSON validation and schema checkinghash computation and verificationstructured data compilationcontradiction detection

Trigger Keywords

Phrases that agents use to match this skill to user intent.

ecc contribution reviewskill submission packetcross-harness validationreview observation compilecontribution contract check

Use Cases

  • Prepare skill contribution review packets for ECC maintainers
  • Validate skill contribution observations against the ECC contract
  • Compile cross-harness skill metadata and evidence into structured proposals
  • Check semantic consistency of skill observations before review submission
  • Generate diagnostic packets for contribution issues and contradictions

Quality Notes

  • Comprehensive contract documentation in SKILL.md, docs/, and references/ explains workflow and expectations clearly
  • Strong test coverage: 45 unit tests including 19 security regressions and 8 review regressions demonstrating defensive coding
  • Explicit safety boundaries: skill does not execute tests, modify source files, run Git commands, or make external API calls; packet is proposal-only
  • Validation is strict and defensive: malformed input, invalid UTF-8, non-finite JSON numbers, path traversal, and unsafe permissions are all rejected
  • Security evidence recorded: Bandit 1.9.4 scan shows zero findings across 915 lines of Python; source hashes embedded to detect drift
  • Output-only semantics: writes capsule file only to new paths (refuses to overwrite); all runner proposals remain unexecuted
  • Authority is explicitly false: all 9 authority fields are hardcoded to false regardless of observation claims; untrusted imports cannot grant permissions
  • Edge cases well-handled: nested JSON depth limits, symlink preservation, concurrent modification detection, schema version validation
  • One minor clarity issue: SKILL.md main body is quite dense; could benefit from a 'Quick Start' section showing a minimal example workflow
Model: claude-haiku-4-5-20251001Analyzed: Nov 17, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use affaan-m/ecc-contribution-review in your dev environment

Command Palette

Search for a command to run...