Repository
m0n0x41d/haft agent skills
- skills
- 24
- GitHub stars
- 1.4k
GitHub description: “Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.”
- Stars
- 1,397 (102 forks)
- Licence
- Unknown
- Last push
- Sep 2026
- Created
- Dec 2025
- Homepage
- haft.tools
- Source
- github.com/m0n0x41d/haft
- ai-agents
- ai-coding
- anthropic
- claude
- claude-code
- developer-tools
- first-principles
- reasoning
- cursor
- cursor-ai
- gemini-cli
- context-memory
- codex
- human-ai-collaboration
- mcp
- systems-engineering
Install all skills
npx skills add m0n0x41d/haftAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in m0n0x41d/haft, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.H Decide Routes one direct, unambiguous operator request to bind a bounded choice as a DecisionRecord. | m0n0x41d/ | 1.4k | — | ~3.5k | Automated safety check: Notes | Unknown | 11 days ago |
| 2 | Generate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each kept visible. | m0n0x41d/ | 1.4k | — | ~1.4k | Automated safety check: Notes | Unknown | 11 days ago |
| 3 | 3.H Frame Shape an engineering problem without assuming a solution or forcing a project phase. | m0n0x41d/ | 1.4k | — | ~1.6k | Automated safety check: Notes | Unknown | 11 days ago |
| 4 | Bootstrap Haft through one readable onboarding surface, prepare an initial profile review or one bounded existing-scope relation change, and orient applicable specification carriers. | m0n0x41d/ | 1.4k | — | ~2.2k | Automated safety check: Notes | Unknown | 11 days ago |
| 5 | 5.H Spec Manage Haft's typed specification lifecycle and source-currentness repair: inspect current SpecSections, draft or clarify carriers, classify FPF semantic fanout, record operator-requested spec… | m0n0x41d/ | 1.4k | — | ~3.4k | Automated safety check: Notes | Unknown | 11 days ago |
| 6 | 6.H Status Read-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module decision coverage, and bounded exact file-link gaps from a… | m0n0x41d/ | 1.4k | — | ~2.3k | Automated safety check: Notes | Unknown | 11 days ago |
| 7 | 7.H Verify Verifies that a recorded DecisionRecord still holds — baseline-vs-measure evidence loop with drift detection per FPF Evidence Decay. | m0n0x41d/ | 1.4k | — | ~3.5k | Automated safety check: Notes | Unknown | 11 days ago |
| 8 | 8.H Note Persist a fact, observation, caveat, or small non-binding rationale in Haft project memory when the operator explicitly asks or current Work supplies a concrete operator-named or agent-inferred… | m0n0x41d/ | 1.4k | — | ~1.1k | Automated safety check: Notes | Unknown | 11 days ago |
| 9 | 9.H Reason Source-first umbrella for FPF-aware reasoning in a Haft project. | m0n0x41d/ | 1.4k | — | ~5.4k | Automated safety check: Notes | Unknown | 11 days ago |
| 10 | 10.H Status Read-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module coverage, and bounded exact file-link gaps from a current code… | m0n0x41d/ | 1.4k | — | ~1.7k | Automated safety check: Pass | Unknown | 11 days ago |
| 11 | 11.H Commission Creates a WorkCommission — bounded execution authority — from an active DecisionRecord. | m0n0x41d/ | 1.4k | — | ~2.4k | Automated safety check: Notes | Unknown | 11 days ago |
| 12 | 12.H Compare Compare two or more existing candidates under an explicit characteristic space, parity basis, and predeclared selection policy. | m0n0x41d/ | 1.4k | — | ~1.7k | Automated safety check: Notes | Unknown | 11 days ago |
| 13 | 13.H Diagnose Diagnose a concrete failure with parallel rival-hypothesis testing. | m0n0x41d/ | 1.4k | — | ~1.1k | Automated safety check: Notes | Unknown | 11 days ago |
| 14 | 14.H Commission Manual-only skill that creates bounded execution authority from an explicit operator grant. | m0n0x41d/ | 1.4k | — | ~576 | Automated safety check: Pass | Unknown | 11 days ago |
| 15 | 15.H Decide Route one direct, unambiguous operator request for a bounded binding choice. | m0n0x41d/ | 1.4k | — | ~629 | Automated safety check: Pass | Unknown | 11 days ago |
| 16 | 16.H Onboard Bootstrap Haft through the readable task-level onboarding surface, prepare a non-binding project-profile review when needed, and orient only applicable typed spec carriers. | m0n0x41d/ | 1.4k | — | ~1k | Automated safety check: Pass | Unknown | 11 days ago |
| 17 | 17.H Reason Source-first umbrella for FPF-aware reasoning in a Haft project. | m0n0x41d/ | 1.4k | — | ~2.7k | Automated safety check: Pass | Unknown | 11 days ago |
| 18 | 18.H Compare Compare two or more existing candidates under an explicit characteristic space, parity basis, and predeclared selection policy. | m0n0x41d/ | 1.4k | — | ~625 | Automated safety check: Pass | Unknown | 11 days ago |
| 19 | 19.H Frame Shape an under-articulated engineering problem without assuming a solution or forcing a project phase. | m0n0x41d/ | 1.4k | — | ~479 | Automated safety check: Pass | Unknown | 11 days ago |
| 20 | 20.H Spec Manage Haft's typed spec lifecycle, source-currentness, carrier edits, and semantic fanout repair. | m0n0x41d/ | 1.4k | — | ~1.5k | Automated safety check: Pass | Unknown | 11 days ago |
| 21 | 21.H Diagnose Diagnose a concrete failure with rival-hypothesis testing. An agent skill from m0n0x41d/haft. | m0n0x41d/ | 1.4k | — | ~312 | Automated safety check: Pass | Unknown | 11 days ago |
| 22 | 22.H Explore Generate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each visible. | m0n0x41d/ | 1.4k | — | ~428 | Automated safety check: Pass | Unknown | 11 days ago |
| 23 | 23.H Note Persist an explicitly requested non-binding fact, observation, caveat, or small rationale in Haft project memory. | m0n0x41d/ | 1.4k | — | ~309 | Automated safety check: Pass | Unknown | 11 days ago |
| 24 | 24.H Verify Verify that a recorded DecisionRecord or claim still holds by comparing its baseline and predictions with current code, tests, measurements, or incidents. | m0n0x41d/ | 1.4k | — | ~229 | Automated safety check: Pass | Unknown | 11 days ago |
Questions, answered from the data.
What is the best skill in m0n0x41d/haft?
H Decide from m0n0x41d/haft ranks first of the 24 skills in m0n0x41d/haft listed here, with the highest score: its repository has 1.4k GitHub stars, its SKILL.md loads about 3.5k tokens and it has informational notes only in the automated safety check. Next come H Explore and H Frame.
Are the skills in m0n0x41d/haft official?
None yet. All 24 skills in m0n0x41d/haft listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from m0n0x41d/haft?
Run npx skills add m0n0x41d/haft in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.