Repository
AHepi/DeepReason agent skills
- skills
- 30
- GitHub stars
- 141
- Stars
- 141 (15 forks)
- Licence
- MIT
- Last push
- Sep 2026
- Created
- Jul 2026
Install all skills
npx skills add AHepi/DeepReasonAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in AHepi/DeepReason, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Orchestrate a Steven Pinker-grounded workflow for teaching, explanatory writing, or material that must do both. | AHepi/ | 141 | — | ~1.5k | Automated safety check: Pass | MIT | 26 days ago |
| 2 | Design, deliver, or audit explanations and lessons with a Pinker-informed focus on phenomena, the curse of knowledge, concrete models, active reasoning, feedback, and revision. | AHepi/ | 141 | — | ~1.8k | Automated safety check: Pass | MIT | 26 days ago |
| 3 | Draft, revise, teach, or audit expository prose using Pinker's cognitive approach to style: classic presentation, reader modeling, curse-of-knowledge repair, coherent information order, deliberate… | AHepi/ | 141 | — | ~2.1k | Automated safety check: Pass | MIT | 26 days ago |
| 4 | Build a battery of concrete instances BEFORE writing or evaluating any definition, pin, or semantic clause (Reed step 1). | AHepi/ | 141 | — | ~811 | Automated safety check: Pass | MIT | 26 days ago |
| 5 | Rules for writing, editing, and retiring skill and workflow files for LLM agents. | AHepi/ | 141 | — | ~1.7k | Automated safety check: Pass | MIT | 26 days ago |
| 6 | Entry point for any DeepReason problem. An agent skill from AHepi/DeepReason. | AHepi/ | 141 | — | ~1.1k | Automated safety check: Pass | MIT | 26 days ago |
| 7 | Router for the code-audit family. An agent skill from AHepi/DeepReason. | AHepi/ | 141 | — | ~1.1k | Automated safety check: Pass | MIT | 26 days ago |
| 8 | Entry point for implementing an operator-suggested change to DeepReason. | AHepi/ | 141 | — | ~1.4k | Automated safety check: Pass | MIT | 26 days ago |
| 9 | Prove the completed change against every acceptance check in SPEC.md and the full DeepReason gate, producing VALIDATION.md. | AHepi/ | 141 | — | ~1.5k | Automated safety check: Pass | MIT | 26 days ago |
| 10 | 10.Deduction Propose machine-checkable derivations in a frozen rule system (treadle deduction stage). | AHepi/ | 141 | — | ~466 | Automated safety check: Pass | MIT | 26 days ago |
| 11 | Protocol for building and maintaining the finite-structure model zoo and running bounded expansion search (Warp W2). | AHepi/ | 141 | — | ~499 | Automated safety check: Pass | MIT | 26 days ago |
| 12 | 12.Term Pinning Protocol for assigning candidate finite meanings to uninterpreted original-side terms of a frozen calculus (Warp W1). | AHepi/ | 141 | — | ~524 | Automated safety check: Pass | MIT | 26 days ago |
| 13 | Question discipline for working DeepReason - route every question to the cheapest authority (record, then framework, then operator), translate the operator's shorthand into typed obligations, and… | AHepi/ | 141 | — | ~2.6k | Automated safety check: Pass | MIT | 26 days ago |
| 14 | Audit dimension - find broken code by running every committed verification instrument and tabling deltas against the recorded baselines. | AHepi/ | 141 | — | ~690 | Automated safety check: Pass | MIT | 26 days ago |
| 15 | Audit dimension - find code that is no longer used, via a reference census over every top-level symbol, one package per invocation. | AHepi/ | 141 | — | ~777 | Automated safety check: Pass | MIT | 26 days ago |
| 16 | Audit dimension - find where documentation deviates from code, using the executable doc checks plus a staleness and unchecked-claims census. | AHepi/ | 141 | — | ~749 | Automated safety check: Pass | MIT | 26 days ago |
| 17 | Audit dimension - verify every ledgered operator design law is actually enforced somewhere in code or gates, so stated goals and shipped behavior cannot silently diverge. | AHepi/ | 141 | — | ~835 | Automated safety check: Pass | MIT | 26 days ago |
| 18 | Audit dimension - find where the code deviates from the spec series and where shipped surface is spec-silent, by a two-direction term census. | AHepi/ | 141 | — | ~752 | Automated safety check: Pass | MIT | 26 days ago |
| 19 | Record an operator's suggested change verbatim and split it into numbered requirements (REQUEST.md). | AHepi/ | 141 | — | ~556 | Automated safety check: Pass | MIT | 26 days ago |
| 20 | Close a validated change tranche — final commit and push, requirement-by-requirement reconciliation against the operator's verbatim words, and the delivery report (DELIVERY.md). | AHepi/ | 141 | — | ~1.1k | Automated safety check: Pass | MIT | 26 days ago |
| 21 | 21.Dr Diagnose Locate the cause of a DeepReason defect from the typed record, not from code reading. | AHepi/ | 141 | — | ~1.6k | Automated safety check: Pass | MIT | 26 days ago |
| 22 | The driving manual for DeepReason - how to run the harness properly (session preflight, the public CLI lifecycle, live-run ladders) and where to look before modifying anything or when diagnosing a… | AHepi/ | 141 | — | ~3.4k | Automated safety check: Pass | MIT | 26 days ago |
| 23 | Execute exactly one unchecked step from CHECKLIST.md, prove its done-criterion, record the output, and stop. | AHepi/ | 141 | — | ~1.9k | Automated safety check: Pass | MIT | 26 days ago |
| 24 | Apply an approved FIX.md to DeepReason with regression tests and the full gate. | AHepi/ | 141 | — | ~1.2k | Automated safety check: Pass | MIT | 26 days ago |
| 25 | Convert an approved SPEC.md into an ordered, checkable step list (CHECKLIST.md) where each step has one done-criterion. | AHepi/ | 141 | — | ~981 | Automated safety check: Pass | MIT | 26 days ago |
| 26 | Design the smallest correct DeepReason fix for a reproduced cause, as FIX.md. | AHepi/ | 141 | — | ~628 | Automated safety check: Pass | MIT | 26 days ago |
| 27 | 27.Dr Reproduce Demonstrate a diagnosed DeepReason cause with the smallest offline artifact — a failing test or a minimal script against the committed record. | AHepi/ | 141 | — | ~719 | Automated safety check: Pass | MIT | 26 days ago |
| 28 | 28.Dr Set Goal Turn a vague DeepReason problem statement into one bounded, falsifiable tranche goal (GOAL.md). | AHepi/ | 141 | — | ~601 | Automated safety check: Pass | MIT | 26 days ago |
| 29 | Translate a captured request into a concrete, bounded change specification (SPEC.md) with per-requirement acceptance checks and recorded assumptions. | AHepi/ | 141 | — | ~2.6k | Automated safety check: Pass | MIT | 26 days ago |
| 30 | Prove a DeepReason fix against its GOAL.md success criterion, optionally with one guarded live run, and record the honest outcome in VERIFY.md. | AHepi/ | 141 | — | ~896 | Automated safety check: Pass | MIT | 26 days ago |
Questions, answered from the data.
What is the best skill in AHepi/DeepReason?
Pinker Clarity Workflow from AHepi/DeepReason ranks first of the 30 skills in AHepi/DeepReason listed here, with the highest score: its repository has 141 GitHub stars, its SKILL.md loads about 1.5k tokens and it passes the automated safety check with no findings. Next come Pinker Teach For Understanding and Pinker Write For Readers.
Are the skills in AHepi/DeepReason official?
None yet. All 30 skills in AHepi/DeepReason 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 AHepi/DeepReason?
Run npx skills add AHepi/DeepReason 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.