All authors
Claude Skills by odysseyalive
github.com/odysseyalive140 skills0 installs160 views
- WorkforceStaff a project with a company of agent employees — CEO, department leads, and ICs, each with a handbook, a pinned model, and a check that proves its work. Existing skills convert in. Commands: audit, hire, retire, handbook, org, principles, review, amend, defect, ledger, roster, model-map, checksums, hooks, preflight, discharge, sweep, backup, restore, rollback, disband, verify, update, version, wrapVotes: 0GitHub stars: 2
- Image Evalfixture stand-inVotes: 0GitHub stars: 2
- Code Evaluator2. Stamp on a clean pass: `{ git diff HEAD; git status --porcelain; } | sha256sum | cut -d' ' -f1 > .claude/.code-eval-reviewed`Votes: 0GitHub stars: 2
- Code Evaluatorfixture stand-inVotes: 0GitHub stars: 2
- Code Evaluatorfixture stand-inVotes: 0GitHub stars: 2
- Ui Designfixture stand-in for the shipped ui evaluatorVotes: 0GitHub stars: 2
- Text EvalEvaluate written prose.Votes: 0GitHub stars: 2
- Text Evalfixture stand-inVotes: 0GitHub stars: 2
- Code EvaluatorThe host's own customized code evaluator, kept by the installer.Votes: 0GitHub stars: 2
- Operating PrinciplesThis project's Strategic Objective and General Operating Principles. Preloaded into every employee.Votes: 0GitHub stars: 2
- Operating PrinciplesThis project's Strategic Objective and General Operating Principles.Votes: 0GitHub stars: 2
- OrgHand a task to the right employee.Votes: 0GitHub stars: 2
- OrgHand a task to the right employee.Votes: 0GitHub stars: 2
- Operating PrinciplesThis project's Strategic Objective and General Operating Principles. Preloaded into every employee.Votes: 0GitHub stars: 2
- Personnel LedgerThis project's personnel records, customized.Votes: 0GitHub stars: 2
- Helper McpA skill whose name ends in -mcp.Votes: 0GitHub stars: 2
- Live Finds PhantomsTest tree. Commands: audit, ghostcmdVotes: 0GitHub stars: 2
- WorkforceFixture skill. Cites maintainer-only bin/ tooling beside one genuinely dead script.Votes: 0GitHub stars: 2
- Remainder Iface Exists| Row | Contract | |---|---| | `Invoke` | `/demo run` | | `Returns` | rows on stdout | | `Fails` | `2` no data |Votes: 0GitHub stars: 2
- Awareness LedgerA knowledge base with no data-skill contract.Votes: 0GitHub stars: 2
- Awareness LedgerThe project's knowledge base.Votes: 0GitHub stars: 2
- Code EvaluatorEvaluate code.Votes: 0GitHub stars: 2
- OtherData sits at .claude/skills/datakeeper/data/rows.csv and is still read. Journal history lives in .claude/workforce/.conversion-journal.md.Votes: 0GitHub stars: 2
- Voice<!-- origin: user | immutable: true --> Never let /skill-builder touch my voice files. <!-- /origin -->Votes: 0GitHub stars: 2
- Code EvaluatorEvaluate code.Votes: 0GitHub stars: 2
- S<!-- origin: user | immutable: true --> > **"Keep my words exactly as I said them."** *— Added 2026-01-01, source: user directive.* <!-- /origin -->Votes: 0GitHub stars: 2
- S<!-- origin: user | immutable: true --> > **"Keep my words exactly as I said them."** *— Added 2026-01-01, source: user directive.* <!-- /origin --> <!-- origin: user | immutable: true --> > **"A second directive, also mine."** *— Added 2026-01-02, source: user directive.* <!-- /origin -->Votes: 0GitHub stars: 2
- BlueprintAuthor an implementation plan as a file, in whatever permission mode the session is already in, without entering plan mode and without implementing what it plans. Use when asked to build, write, draft, or revise a plan, design doc, or implementation strategy for work that happens later, or a living tracker for a long piece of work that spans many sessions. Every claim in the plan cites the tree or is labeled unverified, and the plan is checked before its path is reported. It never offers to s...Votes: 0GitHub stars: 2
- Code EvaluatorEvaluate code to prevent common AI coding mistakes — dead code, duplication, complexity hotspots, reinvented helpers, leftover scaffolding. Two functions plus a pre-write advisor. Use after writing or editing code, when asked to review code quality, clean up the codebase, find unused code, find duplicates, check complexity, or evaluate what an AI just wrote. Commands: review (post-write), sweep (full codebase).Votes: 0GitHub stars: 2
- Image EvalEvaluate images for AI-generation tells and technique authenticity — signature and watermark artefacts, symmetry, metadata provenance (C2PA, generator strings, trainedAlgorithmicMedia), visual clarity, palette variation and set cohesion. Use after generating or selecting images, when asked whether an image reads as AI-generated, or before publishing visual assets. Report-only.Votes: 0GitHub stars: 2
- Security EvaluatorEvaluate a code change for web-security flaws — OWASP Top 10:2025 classes as source-review classes, taint signals from source to sink, and a per-language sink appendix. Use after writing or editing code that handles input, auth, data access, templating, deserialization, or external requests; when asked to security-review a change, check for injection/XSS/SSRF/authz flaws, or evaluate the security of what was just written. Report-only, candidate-tier by construction.Votes: 0GitHub stars: 2
- Text EvalEvaluate written prose for AI-generation tells and register drift — mechanical character and punctuation defects, clustered judgment-class signals, citation integrity, and conversational register. Use after writing or editing any prose a person will read, when asked to check whether text reads as AI-generated, or before publishing copy. Grades against a cited catalog with clustering thresholds and hard rows that fire on first occurrence. Report-only.Votes: 0GitHub stars: 2
- Ui DesignEvaluate a RENDERED interface for design quality — declared-vs-rendered slots (no missing or placeholder art), applied theme vs framework default, visual hierarchy, typography, colour roles, CTA, WCAG 2.2 AA contrast and focus, reflow at 320 CSS pixels, and AI-slop/templated-default tells. Use after a UI-shipping change is written, when asked to design-review a page, or to decide whether a surface looks right to ship. Grades against a cited catalog with stable rule IDs and BLOCKS on hard-fail...Votes: 0GitHub stars: 2
- New<!-- origin: user | immutable: true --> > **"This block has no row yet."** *— Added 2026-09-17, source: user directive.* <!-- /origin -->Votes: 0GitHub stars: 2
- Text Evalfixture stand-in for the shipped text evaluatorVotes: 0GitHub stars: 2
- Image Evalfixture stand-in for the shipped image evaluatorVotes: 0GitHub stars: 2
- Text Evalthe project's own older text evaluatorVotes: 0GitHub stars: 2
- Text Evalfixture stand-in for the shipped evaluatorVotes: 0GitHub stars: 2
- Shared ArtifactThe house style for any shareable online artifact — a claude.ai Artifact, a published HTML page, a report or brief someone will be sent a link to. Use before writing or republishing any artifact page, when asked to create, share, publish or clean up an online artifact, and when deciding between an HTML page and a Claude Docs document. Carries the token set, the dark-mode contract, the briefing-binder layout, a starter template, and the sharing hygiene rules.Votes: 0GitHub stars: 2
- Code Evaluatorfixture stand-in for the shipped evaluatorVotes: 0GitHub stars: 2