All authors
Claude Skills by eranw2000
github.com/eranw200012 skills0 installs14 views
- Project StatusCold-start orientation for a project. Gathers git state, open PRs against main, Render deploy health, local Docker container status, OpenSpec change progress, unresolved review Blockers in COMMENTS.md, and pending items from project memory, then synthesizes a "what's the state of this project right now" report. Use when sitting back down on a project after time away ("where was I", "catch me up", "what's the state", "status check"). Read-only, never mutates git, gh, Render, Docker, or project...Votes: 0GitHub stars: 5
- Salvage Session ArchivesMine the Claude Code session-transcript leftover folders for a given project, extract any facts/decisions/gotchas not already captured in the project CLAUDE.md, append them under a "Salvaged from session archives" section after a duplicate/contradiction cross-check, then delete the leftover folders. Use when the user says "salvage the session archives", "extract leftover transcripts", "collect important information from the leftover folders".Votes: 0GitHub stars: 5
- Split Claude MdSix-phase CLAUDE.md cleanup for a file that has grown too large. Phase 0 deletes what the repository itself answers. Phase A rotates old dated records into monthly archives with an index and a navigation header. Phase B consolidates recurring failure patterns into a Known Patterns section with current instance counts. Phase C extracts stable reference sections to sibling files or to a skill, leaving a pointer. Phase D keeps a rule in place and moves only its evidence to a satellite, for alway...Votes: 0GitHub stars: 5
- Save Script To SkillTurn a script Claude wrote during a skill run into a permanent tool of that skill. Finds the skill last invoked in the session and the script written or run after it (from the session transcript, so a summarized conversation cannot hide it), makes it reusable (arguments instead of hard-coded session values, no secrets, clear exit codes), saves it in the skill's scripts folder, runs it once, and rewrites the skill's SKILL.md so future runs execute the file instead of writing it again. Use when...Votes: 0GitHub stars: 5
- Pr CheckpointSnapshot in-progress work as a GitHub PR and rebuild the local Docker container so you can test the feature branch on localhost. Does NOT merge, does NOT touch production, does NOT update README or CLAUDE.md (premature; that happens at /release time). Use when you want to capture a checkpoint of feature work, open a PR for review, and test locally before deciding it's ready to ship. Triggers on "checkpoint", "open a PR", "draft a PR", "snapshot this", "let me test this locally".Votes: 0GitHub stars: 3
- ReleaseShip to production. The single "ship it" verb for any project, handling both PR mode (merges open PRs targeting main) and trunk mode (commits straight to main). Updates README.md + project CLAUDE.md, pushes to all remotes, verifies the auto-deploy (Render / Vercel / etc.), and rebuilds the local Docker container so localhost matches prod. Triggers on "release", "ship it", "deploy", "ship to prod", "merge and release", "push to prod".Votes: 0GitHub stars: 3
- Review RoundRun the codified reviewer loop on a diff or PR: author adversarial per-agent prompts pointing at the riskiest spots, launch whichever of code-reviewer, deploy-guard and pr-validator the user picks when asked, in parallel, bring the findings to the user and let them choose what is worth fixing, reproduce by execution each one they pick before fixing it, prove each fix with a non-vacuous regression test, and post the PR verdict comment that /release gates on. Use before shipping, or when the us...Votes: 0GitHub stars: 3
- Draw DiagramProduce a diagram as a draw.io (.drawio) file, then validate and render it to PNG/SVG so it can be visually checked before reporting done. Covers architecture, data flow, sequence, decision tree, system map, ER diagram, org chart, network topology, state machine, infrastructure layout, and workflow automation flows such as Power Automate. Use whenever a diagram is needed for any project (draw.io is the default over Mermaid / Graphviz / ASCII), or when the user says "draw a diagram", "make a f...Votes: 0GitHub stars: 3
- Dependency ReviewReview the dependencies a branch adds or changes for known CVEs, license compliance, supply-chain risk, and unnecessary additions, across Python (pip/Poetry), JS/TS (npm/pnpm), and Java/C# (Maven/Gradle/NuGet). Produces DEPENDENCY-COMMENTS.md anchored to SEC-DEP-* rules. Use when a PR touches a manifest or lockfile, or when the user says "dependency review", "check dependencies", "SCA", "supply chain", "are these packages safe", "license check".Votes: 0GitHub stars: 3
- Privacy ReviewReview a feature branch for data-protection compliance (GDPR + CCPA) against the org privacy standards. Produces PRIVACY-COMMENTS.md with severity bands (Blocker, Major, Nit, Question), each anchored to a PRIV-* rule. Use after development and before a PR when the change touches personal data, or when the user says "privacy review", "check GDPR", "data protection review", "PII review". This is the privacy counterpart to security-review; it covers what security review does not (retention, dele...Votes: 0GitHub stars: 3
- Secrets RemediationGuided playbook for when a secret has leaked into the repo or git history (rotate, remove, scrub, verify), and for hardening so it does not recur. Use when a secret scan fired, when the user says "a key got committed", "we leaked a secret", "rotate this credential", "scrub git history", "remove secret from history", or after secret-scan / gitleaks blocks a commit. Detection without remediation just creates panic; this is the remediation half.Votes: 0GitHub stars: 3
- Threat ModelProduce a design-time threat model for a feature or system, using STRIDE for security threats and LINDDUN for privacy threats, anchored to the org standards. Writes THREAT-MODEL.md with identified threats, their severity, and mitigations that become NFR-SEC-* / NFR-PRIV-* requirements. Use during design (feeds the architect skill) or when the user says "threat model", "STRIDE", "LINDDUN", "what could go wrong with this design", "attack surface". Design-time and proactive, unlike security-revi...Votes: 0GitHub stars: 3