Skip to content
Skills Library
Programming · Analysis

code-gap-sweeping

/code-gap-sweeping

Sweep one or more local repositories for implementation gaps and produce deterministic, evidence-backed remediation lanes. Use when you need cross-repo detection of missing tests, docs lockstep drift, risky TODO/FIXME additions, and release-hygiene misses.

Licence
MIT
Last repository change
28.08.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
6
Scripts
2
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 28.08.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 2 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/code_gap_sweep.py, scripts/repo_family_pipeline.py

What it does and when to use it

Sweep one or more local repositories for implementation gaps and produce deterministic, evidence-backed remediation lanes. Use when you need cross-repo detection of missing tests, docs lockstep drift, risky TODO/FIXME additions, and release-hygiene misses.

Original author description

Sweep one or more local repositories for implementation gaps and produce deterministic, evidence-backed remediation lanes. Use when you need cross-repo detection of missing tests, docs lockstep drift, risky TODO/FIXME additions, and release-hygiene misses.

How it works

  1. Workflow
  2. Canonical Run
  3. Scope Boundary
  4. Gap Contracts
  5. Triage Mapping
  6. Output
  7. References
  8. Loopback
Original SKILL.md headings · 111 lines, 385 words
SKILL.md preview
---
name: code-gap-sweeping
description: Sweep one or more local repositories for implementation gaps and produce deterministic, evidence-backed remediation lanes. Use when you need cross-repo detection of missing tests, docs lockstep drift, risky TODO/FIXME additions, and release-hygiene misses.
---

# Code Gap Sweeping

Use this skill to run a repeatable cross-repo gap scan and convert findings into concrete follow-up actions.

## Workflow

1. Run the gap sweep script across one or more local repos.
2. Review severity-ranked findings (`critical`, `high`, `medium`).
3. Route each finding into the smallest existing skill lane that can fix it.
4. Emit machine-readable evidence for admission, planning, and release notes.
5. For repeated multi-repo operations, generate a deterministic repo-family command matrix.

## Canonical Run

```bash
python3 "$CODEX_HOME/skills/code-gap-sweeping/scripts/code_gap_sweep.py" \
  --repo "<PRIVATE_REPO_A>=/path/to/<PRIVATE_REPO_A>" \
  --repo "<PRIVATE_REPO_B>=/path/to/<PRIVATE_REPO_B>" \
  --since-days 14 \
  --json-out /tmp/code-gap-sweep.json
```

One-command sweep for all repos under a workspace root:

```bash
python3 "$CODEX_HOME/skills/code-gap-sweeping/scripts/code_gap_sweep.py" \
  --repos-root "$env:USERPROFILE\\Documents\\GitHub" \
  --exclude-repo "docs" \
  --since-days 14 \
  --json-out /tmp/code-gap-sweep-all.json
```

Working-tree focused sweep during active local edits:

```bash
python3 "$CODEX_HOME/skills/code-gap-sweeping/scripts/code_gap_sweep.py" \
  --repo "skill-arbiter=." \
  --diff-mode working-tree \
  --json-out /tmp/code-gap-sweep-working-tree.json
```

Full pipeline matrix for repo families (`repo_a`/`repo_b`/`repo_c`/`repo_d`):

```bash
python3 "$CODEX_HOME/skills/code-gap-sweeping/scripts/repo_family_pipeline.py" \
  --repo "<PRIVATE_REPO_A>=/path/to/<PRIVATE_REPO_A>" \
  --repo "<PRIVATE_REPO_B>=/path/to/<PRIVATE_REPO_B>" \
  --repo "<PRIVATE_REPO_C>=/path/to/<PRIVATE_REPO_C>" \
  --repo "<PRIVATE_REPO_D>=/path/to/<PRIVATE_REPO_D>" \
  --family "<PRIVATE_REPO_A>=repo_a" \
  --family "<PRIVATE_REPO_B>=repo_b" \
  --family "<PRIVATE_REPO_C>=repo_c" \
  --family "<PRIVATE_REPO_D>=repo_d" \
  --since-days 14 \
  --json-out /tmp/repo-family-pipeline.json \
  --bash-out /tmp/repo-family-pipeline.sh
```

## Scope Boundary

Use this skill when the primary task is detecting and prioritizing implementation gaps across repositories.

Do not use this skill for:

1. Skill install/quarantine decisions (use `skill-arbiter-lockdown-admission`).
2. Skill discovery portfolio curation (use `skills-discovery-curation`).
3. Repo-specific deep debugging where a dedicated repo skill exists.

## Gap Contracts

The script detects deterministic gap categories:

1. `tests_missing`: code changed without corresponding test changes.
2. `docs_lockstep_missing`: behavior-impacting files changed without docs updates.
3. `todo_fixme_added`: newly introduced `TODO`/`FIXME` markers in the patch window.
4. `release_hygiene_missing`: release-impacting changes without `pyproject.toml` + `CHANGELOG.md` updates.

## Triage Mapping

Route findings consistently:

1. `tests_missing` -> repo-specific execution/test lane.
2. `docs_lockstep_missing` -> `docs-alignment-lock`.
3. `todo_fixme_added` -> repo-specific cleanup lane, then re-sweep.
4. `release_hygiene_missing` -> `skill-arbiter-release-ops`.

## Output

JSON report includes:

- scan metadata (`generated_at`, `since_days`, repo list)
- per-repo findings with severity and evidence
- aggregate counters by category and severity
- suggested skill lanes for remediation

## References

- `references/gap-rubric.md`
- `scripts/code_gap_sweep.py`
- `references/repo-family-pipeline.md`
- `scripts/repo_family_pipeline.py`

## Loopback

If this lane is unresolved, blocked, or ambiguous:

1. Capture the JSON report path and unresolved findings.
2. Route back through `$skill-hub` for chain recalculation.
3. Resume only after the updated chain returns a deterministic next step.
Files in this package (6)
  • SKILL.md 4 KB
  • agents/openai.yaml 1 KB
  • references/gap-rubric.md 1 KB
  • references/repo-family-pipeline.md 2 KB
  • scripts/code_gap_sweep.py 16 KB
  • scripts/repo_family_pipeline.py 19 KB

Versions

The database has no other skills named code-gap-sweeping.

Database snapshot: 13.11.2026 · package version ff682c8c5c2d (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 84scan-todos
    Sweep source comments, not tracker items, for TODO/FIXME/HACK/XXX markers and resolve or file each one. Use when: 'scan TODOs', 'scan for FIXME', 'sweep the codebase for markers', 'find TODO comments', 'resolve TODO/FIXME/HACK', 'scan for tech-debt comments', 'clean up markers'.…
  • 100import-todos
    Discover TODO/FIXME comments in the codebase and convert selected ones into task files. Use when the user wants to turn code TODOs into tracked tasks.
  • 100import-todos
    Discover TODO/FIXME comments in the codebase and convert selected ones into task files. Use when the user wants to turn code TODOs into tracked tasks.
  • 100todo-sweep
    Triages the TODO and FIXME comments of the code in a local panel - each comment becomes a card, oldest first (age from git blame), the user marks Resolve, Discard or Keep (pt-BR Resolver, Descartar, Manter), and the result is a read-only report; no source file is edited. Use…
  • 100fill-the-gaps
    Complete work in progress that the user left incomplete on purpose. Use when the tree holds bare signatures, empty modules, pseudo code, deleted code, or `AI TODO` / `AI FIXME` / `AI NOTE` markers.
  • 100accelint-ts-documentation
    Audit and improve JavaScript/TypeScript documentation including JSDoc comments (@param, @returns, @template, @example), comment markers (TODO, FIXME, HACK), and code comment quality. Use when asked to 'add JSDoc', 'document this function', 'audit documentation', 'fix comments',…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.