skills/work-log-writer/SKILL.md
Use only when the user explicitly names the work-log-writer skill; never auto-activate from generic work log, daily log, EOD summary, status update, or date-range summary requests.
npx skillsauth add narumiruna/agent-skills work-log-writerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Write concise work logs for a specified date range in the current git repository. Do not use this skill unless the user explicitly invokes $work-log-writer or names work-log-writer.
Operate on one git repository at a time. Do not write files unless the user explicitly asks for a saved note or file update.
Resolve the requested range before collecting evidence.
Use concrete dates in the final title, not relative labels.
Example commands:
date +%F
git config user.name
git config user.email
git log --since="2026-05-01 00:00" --until="2026-05-05 23:59:59" --date=iso --pretty=format:"%h%x09%ad%x09%an <%ae>%x09%s"
Start from commits in the resolved range.
git config user.name or git config user.email identifies them. If the current author cannot be determined, ask whether to summarize only the user's own commits.git show --stat <sha> or git show --name-only <sha> before summarizing.git status --short and git diff --stat.Required format:
# Work Log - <resolved date range>
- ...
- ...
- ...
Use a title that includes the resolved date range. Keep the body as a single flat bullet list with no sections or subheadings. Each bullet should describe one high-level work item, progress point, blocker, or follow-up. Prefer concise summaries over implementation details, and order bullets from highest to lowest team impact. If team impact is unclear, use the evidence to prioritize likely cross-team/customer impact, risk reduction, unblockers, and follow-ups before lower-impact implementation details.
Do not guess what the user completed. If evidence is insufficient, either mark the uncertainty in a bullet or ask for the minimum missing context needed to proceed.
development
Score or compare one or more agent skills across trigger clarity, workflow actionability, safety boundaries, verification rigor, incremental knowledge value, and leanness. Use only when the user explicitly asks for ratings, numerical quality scores, rubric-based scorecards, or scored comparisons; use creating-agent-skills for unscored reviews or revisions.
development
Assess or improve an existing codebase's architecture when the user asks about module boundaries, coupling, scattered ownership, testability, change locality, deep modules, seams, or behavior-preserving structural refactoring. Use for cross-module design rather than ordinary diff review or a confirmed edge-case bug fix.
development
Perform read-only security audits, vulnerability assessments, or threat-focused reviews of diffs, pull requests, code paths, or explicitly scoped repositories when security is the primary objective or acceptance criterion. Use reviewing-code for ordinary review with baseline security coverage and hardening-code-paths for fixing confirmed findings.
development
Run iterative multi-reviewer panels over a code diff, verify their findings, apply explicitly authorized fixes, and re-review the updated change until it passes or reaches a stopping condition. Use when the user asks for a panel loop, multi-model code-review consensus, or a review-fix-re-review cycle.