All authors
Claude Skills by MalikKhaledSaid
github.com/MalikKhaledSaid6 skills4 installs21 views
- agent-token-auditor-liteFree token audit for Claude Code. Reads the user's own local session logs and reports tokens by session, day and model, then names the costly patterns (long sessions, subagent fan-out, cache rebuilds, large tool outputs, one model for everything) with a one-line fix each. Use when the user hits usage limits or asks where their Claude Code tokens or usage went. Search words: Claude Code token usage, usage limit, rate limit, token cost, context window, session cost report.Votes: 0
- release-gate-liteFree pre-release check for a git repository. Gives one verdict, PASS, HOLD or FAIL, from checks for leaked secrets in tracked files, version agreement across manifest files, version bump since the last tag, a changelog entry, merge conflict markers and a clean working tree. Use before tagging or publishing a release, or when the user asks "is this ready to ship" or "check before release". Search words: pre-release check, release checklist, pre-publish check, secret scan, version bump check, c...Votes: 0
- lessons-log-liteFree check for a LESSONS.md file of standing rules. Finds rules with no evidence, repeated ids, review dates that passed, missing dates, rules that are too long, rules with the same title and a file that grew too big. Use when the user asks to check, review or clean up LESSONS.md, or wants to know whether the team's lessons are still current.Votes: 0
- numbers-check-liteFree check that every number in a Markdown report has a label (verified, inferred, unverified or not found), a source and a time. Use before sending a report, a status update or a decision memo that holds figures, or when the user asks whether the numbers in a document can be trusted.Votes: 0
- research-brief-liteFree check for a Markdown research brief. Finds a missing question, search budget, stop rule or findings section, a claim with no label ([V] verified, [I] inferred, [U] unverified, [X] not found) and a verified claim with no source. Use when an agent researches a market, a tool or a question, when the user asks for a research brief or a fact-checked summary, or before sharing research. Search words: research brief, fact check, source check, citations, search budget, stop rule, deep research.Votes: 0
- agent-team-check-liteFree health check for a team of AI agent sessions that share ORG.md, TEAM_PLAN.md and DECISIONS.md. Finds a role that has no queue, a broken reporting line, more than one voice to the human, tasks with no goal or receiver, template text left in the plan, a stale plan or decision log, and missing session ids. Use when the user runs several Claude Code sessions as a team and asks whether the team files are healthy. Search words: agent team setup, multi-agent team, agent org chart, team plan che...Votes: 0