Rules Distillation
affaan-m/ECC
Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.
Propose machine-checkable derivations in a frozen rule system (treadle deduction stage).
MITAuto-check passed
Install Deduction
$ npx skills add AHepi/DeepReason --skill deduction -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AHepi/DeepReason deduction --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deduction .claude/skills/deduction && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "deduction" agent skill from https://github.com/AHepi/DeepReason/tree/main/skills/deduction into .claude/skills/deduction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deduction", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AHepi/DeepReason/tree/main/skills/deductionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AHepi/DeepReason --skill deduction -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AHepi/DeepReason deduction --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/deduction .agents/skills/deduction && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "deduction" agent skill from https://github.com/AHepi/DeepReason/tree/main/skills/deduction into .agents/skills/deduction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deduction", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AHepi/DeepReason --skill deduction -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AHepi/DeepReason deduction --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/deduction .cursor/skills/deduction && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "deduction" agent skill from https://github.com/AHepi/DeepReason/tree/main/skills/deduction into .cursor/skills/deduction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deduction", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AHepi/DeepReason.git --path skills/deduction--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AHepi/DeepReason --skill deduction -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AHepi/DeepReason deduction --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/deduction .gemini/skills/deduction && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "deduction" agent skill from https://github.com/AHepi/DeepReason/tree/main/skills/deduction into .gemini/skills/deduction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deduction", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AHepi/DeepReason deductionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AHepi/DeepReason --skill deduction -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/deduction .github/skills/deduction && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "deduction" agent skill from https://github.com/AHepi/DeepReason/tree/main/skills/deduction into .github/skills/deduction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deduction", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AHepi/DeepReason --skill deduction -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AHepi/DeepReason deduction --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AHepi/DeepReason.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/deduction .opencode/skills/deduction && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "deduction" agent skill from https://github.com/AHepi/DeepReason/tree/main/skills/deduction into .opencode/skills/deduction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deduction", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
deduction- GitHub stars
- 141
- Token cost
- ~466 tokens
- SKILL.md length
- 212 words
- Files
- 1
- Skills in repo
- 30
- Repo updated
- First seen
- Licence
- MIT
At a glance
Propose machine-checkable derivations in a frozen rule system (treadle deduction stage).
- Works in 6 steps: Output exactly one derivation file… → One rule application per step. No gaps,… → Formulas are written in the theory's… → …
- Proof-search tasks where the target is a theory row and acceptance replays every step with derivationcheck.py
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Deduction is an agent skill from AHepi/DeepReason. Propose machine-checkable derivations in a frozen rule system (treadle deduction stage). Use for proof-search tasks where the target is a theory row and acceptance replays every step with derivationcheck.py. One rule application per step, everything cited, honest grades, CANNOTDERIVE as a first-class outcome.
Its SKILL.md is about 470 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The licence is MIT.
When your agent uses it
- Proof-search tasks where the target is a theory row and acceptance replays every step with derivationcheck.py
Example prompts
- “/deduction”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Output exactly one derivation file conforming byte-exactly to the
- One rule application per step. No gaps, no "clearly", no combined
- Formulas are written in the theory's s-expression condition language,
- Grades are honest: a step never claims more authority than the
- When the checker fails you, the error is STEP-ADDRESSED. Repair the
- If you cannot complete a derivation within your budget, emit
What it can do on your machine
Read from SKILL.md and the folder at commit 9607fba. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Deduction loads about 466 tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 212 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from AHepi/DeepReason at commit 9607fba, republished under its MIT licence (© AHepi). 212 words, ~466 tokens.
Download SKILL.mdSave it as
.claude/skills/deduction/SKILL.md (or your agent's skills folder).- name
- deduction
- description
- Propose machine-checkable derivations in a frozen rule system (treadle deduction stage). Use for proof-search tasks where the target is a theory row and acceptance replays every step with derivation_check.py. One rule application per step, everything cited, honest grades, CANNOT_DERIVE as a first-class outcome.
Deduction (proof search under replay)
<!-- PROMPT-CORE-BEGIN -->You propose derivations; a deterministic checker replays them. Your proposal has no authority until every step replays.
- Output exactly one derivation file conforming byte-exactly to the READ-ONLY REFERENCE grammar (zoo/derivations/FORMAT.md) and using ONLY rule ids from the READ-ONLY REFERENCE rules profile. If either reference is absent from your context, report BLOCKED.
- One rule application per step. No gaps, no "clearly", no combined steps. Every premise cited by step id; PREMISE leaves cite theory row ids and state no formula.
- Formulas are written in the theory's s-expression condition language, byte-exactly -- the conclusion must equal the target row's condition as bytes, not as a paraphrase.
- Grades are honest: a step never claims more authority than the propagation rule allows from its premises.
- When the checker fails you, the error is STEP-ADDRESSED. Repair the addressed step; do not reshuffle the whole proof to route around a misunderstanding you have not diagnosed.
- If you cannot complete a derivation within your budget, emit BLOCKED.md containing CANNOT_DERIVE, the closest partial derivation, and which gap defeated you. NEVER pad a pseudo-proof to look complete, and NEVER claim non-derivability -- your failure to find a route is evidence about you, not about the calculus; non-entailment claims belong to countermodel search.
<!-- PROMPT-CORE-END -->© AHepi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/deduction of AHepi/DeepReason.
Open the folder on GitHubat commit 9607fba
Compare with similar skills
Deduction next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Deduction this skillAHepi/DeepReason | 141 | — | ~466 | Automated safety check: Pass | MIT | |
| Rules Distillationaffaan-m/ECC | 275k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Geo Proposalsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Codex Rules Referencecode-yeongyu/oh-my-openagent | 70k | — | ~269 | Automated safety check: Pass | Custom licence | |
| Better Proposals AutomationComposioHQ/awesome-claude-skills | 77k | 3 repos | ~764 | Automated safety check: Pass | None | |
| Contract And Proposal Writeralirezarezvani/claude-skills | 28k | 2 repos | ~3.4k | Automated safety check: Pass | MIT |
Similar skills
Geo Proposal
sickn33/agentic-awesome-skills
Auto-generate a professional, client-ready GEO service proposal from audit data.
Codex Rules Reference
code-yeongyu/oh-my-openagent
Explains how the Codex Rules plugin injects project instructions and file-specific rules into a session, which rule files it reads and which settings control it.
Better Proposals Automation
ComposioHQ/awesome-claude-skills
Automate Better Proposals tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.
Contract And Proposal Writer
alirezarezvani/claude-skills
Generate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, NDAs, and MSAs.
Proposal
Chorus-AIDLC/Chorus
Chorus Proposal workflow on Hermes — create proposals with document and task drafts, manage dependency DAG, validate, submit, and run the read-only proposal reviewer via delegatetask.
More from AHepi/DeepReason
All 30 skills in this repoPinker Clarity Workflow
AHepi/DeepReason
Orchestrate a Steven Pinker-grounded workflow for teaching, explanatory writing, or material that must do both.
Pinker Teach For Understanding
AHepi/DeepReason
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.
Pinker Write For Readers
AHepi/DeepReason
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…
Example Battery
AHepi/DeepReason
Build a battery of concrete instances BEFORE writing or evaluating any definition, pin, or semantic clause (Reed step 1).
Authoring Skills
AHepi/DeepReason
Rules for writing, editing, and retiring skill and workflow files for LLM agents.
Deepreason Orchestrator
AHepi/DeepReason
Entry point for any DeepReason problem. An agent skill from AHepi/DeepReason.
Questions about Deduction
What does Deduction do?
Propose machine-checkable derivations in a frozen rule system (treadle deduction stage). Deduction is an agent skill from AHepi/DeepReason. Propose machine-checkable derivations in a frozen rule system (treadle deduction stage).
When should I use Deduction?
Deduction fits situations like: proof-search tasks where the target is a theory row and acceptance replays every step with derivationcheck.py.
How do I install Deduction in Claude Code?
Run `npx skills add AHepi/DeepReason --skill deduction -a claude-code`. Or copy the skill folder (skills/deduction in AHepi/DeepReason) into .claude/skills/deduction in your project. Claude Code loads it when a task matches its description.
How do I install Deduction in Codex?
Run `npx skills add AHepi/DeepReason --skill deduction -a codex`. Or copy the skill folder (skills/deduction in AHepi/DeepReason) into .agents/skills/deduction in your project. Codex loads it when a task matches its description.
Can I use Deduction in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AHepi/DeepReason --skill deduction -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deduction, .gemini/skills/deduction, .github/skills/deduction and .opencode/skills/deduction in your project.
What does Deduction need to run?
SKILL.md names no scripts, command-line tools or credentials: Deduction is instructions for the agent only.
Does Deduction access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Deduction safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Deduction use?
Deduction is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Deduction use?
About 466 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Deduction?
Skills that share tags, products or a category with Deduction: Rules Distillation (affaan-m/ECC, 275k stars), Geo Proposal (sickn33/agentic-awesome-skills, 47k stars), Codex Rules Reference (code-yeongyu/oh-my-openagent, 70k stars) and Better Proposals Automation (ComposioHQ/awesome-claude-skills, 77k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Deduction?
AHepi (a GitHub user) maintains it in AHepi/DeepReason, which has 141 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on September 10, 2026.
Source: AHepi/DeepReason on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.