RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Diff/tjboudreaux-cc-thinking-skills-claude ↔ tjboudreaux-cc-thinking-skills-agents

Comparison

A · CLAUDE.md · tjboudreaux/cc-thinking-skillsB · AGENTS.md · tjboudreaux/cc-thinking-skills
What each file covers, counted
DimensionSharedOnly in AOnly in BOverlap
Sections0170%
Commands100100%
Section tags10325%

What each file covers

Sections

0 shared · 1 only in A · 7 only in B
  • − Claude Project Notes
  • + Agent Guidelines
  • + First Principles
  • + Skill Authoring & Eval Standards
  • + Default Workflow
  • + Verification
  • + Local Backups
  • + Images

Commands

1 shared · 0 only in A · 0 only in B
  •   node scripts/validate-skills.js

Section tags

1 shared · 0 only in A · 3 only in B
  • + code-style
  • + security
  • + do-not
  •   agent-behaviour

Line diff

+47 added−13 removed5 unchanged9.6% identical
tjboudreaux/cc-thinking-skills · CLAUDE.md
@@ −1 @@
1# Claude Project Notes
2 
3Follow `AGENTS.md` for repository workflow.
4 
5Key project facts:
6- Shipped skill count: 28.
7- `thinking-scientific-method` is the shipped hypothesis-differential debugging skill. Do not reintroduce a separate v2 variant.
8- Eval claims must identify whether they are pre-edit, post-edit, directional, or statistically significant.
9- Backups of global Claude state belong in `backups/` and must remain uncommitted.
10 
11Common verification commands:
12 
13```bash
14node scripts/validate-skills.js
15EVAL_RUN=local node evals/run-structural.js
16EVAL_RUN=local node evals/run-routing.js
17```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18 
tjboudreaux/cc-thinking-skills · AGENTS.md
@@ +1 @@
1# Agent Guidelines
2 
3This repository packages 28 Claude Code thinking skills. Treat it as a plugin marketplace project first and an eval research project second.
4 
5## First Principles
 
 
 
 
6 
7Every change to this project must serve at least one of these goals, and any major change should state which one:
8 
91. **Maximize model performance per task** — raise measured task success of the skills and harness, across frontier SoTA models and smaller/cheaper models alike.
102. **Reduce token usage / cost per task** — at equal or better measured performance.
11 
12A change that does neither is noise. A change that trades one goal against the other must say so and show the measurement. Treat every token in a skill description or body as a cost charged against these goals: descriptions are paid on every model invocation, bodies on every skill trigger. Performance claims must name the model class measured; a win on a frontier model that harms a smaller model (or the reverse) is not a proven win.
13 
14## Skill Authoring & Eval Standards
15 
16Distilled from "Don't Ship Skills Without Evals" (Philipp Schmid, Google DeepMind) and "How I deleted 95% of my agent skills and got better results" (Nick Nisi, WorkOS):
17 
18- **Never ship a skill change without eval evidence.** Run the relevant evals on every skill diff; merge only when evals improve or coverage grows. Current post-edit evidence only — historical pre-edit results are context, not proof.
19- **Measure, don't assume.** More tokens and more instructions do not imply better performance; a loaded skill can actively hurt (documented case: 97% correct without a skill, 77% with it). Trust is a pass rate, not a vibe.
20- **Run ablations.** Evaluate with and without the skill. Retire a capability skill (one that teaches what the base model can't yet do) when the model matches it unaided — models improve and evals tell you when. Preference skills (this project's conventions) are durable; protect them with regression evals. Keep the eval after retiring the skill as the guard that says when to reintroduce it.
21- **Guide, don't prescribe.** Skills encode gotchas, landmines, and decision boundaries — not documentation summaries. Reference point: 10,000 generated lines cut to 553 hand-written gotcha lines raised accuracy and cut eval runtime from 68 to 6 minutes.
22- **Write directives, not essays.** Tell the agent when to use the skill and when not to; keep the required "When NOT to Use" boundary sharp and back it with negative trigger evals.
23- **Keep skills lean and layered.** Target under 500 words per SKILL.md; push depth into reference files (progressive disclosure). The frontmatter description is the always-paid cost — every word must change routing behavior.
24- **Kill no-ops.** Delete any instruction that does not change agent behavior ("write clean code", "be thorough"). Every retained line must pay for its tokens.
25- **Scripts for deterministic work.** If a workflow is always the same, make it a script the agent calls — not prompt content the model re-derives at token cost.
26- **Enforce, don't instruct.** Put must-happen checks in code — validators, gates, hashes, state machines — not in prose the model can skip or fake. Require verifiable artifacts (output hashes, logs, recorded runs) for claimed results.
27- **Test outcomes, not paths; test early.** A handful of positive plus negative prompts per skill beats none. Prefer cheap deterministic asserts (regex/exact match) over LLM judges; run multiple trials before trusting a result (agents are non-deterministic); isolate eval runs so agents cannot mine prior state.
28- **Every failure becomes harness data.** Feed eval failures back into skill gotchas, datasets, or gates — fix the harness, not just the output.
29 
30## Default Workflow
31 
32- Preserve the public skill count at 28 unless a change intentionally adds/removes a shipped skill and updates README, plugin metadata, routing cases, and eval docs together.
33- Keep skill frontmatter descriptions situation-named and under 200 characters.
34- Prefer agent-native instructions over human facilitation language.
35- Add explicit "When NOT to Use" boundaries for every non-router skill.
36- Do not commit local backups, downloaded third-party datasets, transient logs, or scratch eval runs.
37 
38## Verification
39 
40- Run `node scripts/validate-skills.js` after skill edits.
41- Run `EVAL_RUN=<name> node evals/run-structural.js` after catalog edits.
42- Run routing or behavioral evals only when the changed surface warrants the cost.
43- Use current post-edit evidence only; historical pre-edit results are context, not proof.
44 
45## Local Backups
46 
47Global Claude assets may be backed up under `backups/` for safety. The directory is gitignored. Do not add backup archives to commits.
48 
49## Images
50 
51README and marketing images live in `assets/`. Keep generated source paths out of README links; copy selected assets into the repo and leave generator cache files untouched.
52 
@@ −1 +1 @@
1−# Claude Project Notes
1+# Agent Guidelines
22  
3−Follow `AGENTS.md` for repository workflow.
3+This repository packages 28 Claude Code thinking skills. Treat it as a plugin marketplace project first and an eval research project second.
44  
5−Key project facts:
6−- Shipped skill count: 28.
7−- `thinking-scientific-method` is the shipped hypothesis-differential debugging skill. Do not reintroduce a separate v2 variant.
8−- Eval claims must identify whether they are pre-edit, post-edit, directional, or statistically significant.
9−- Backups of global Claude state belong in `backups/` and must remain uncommitted.
5+## First Principles
106  
11−Common verification commands:
7+Every change to this project must serve at least one of these goals, and any major change should state which one:
128  
13−```bash
14−node scripts/validate-skills.js
15−EVAL_RUN=local node evals/run-structural.js
16−EVAL_RUN=local node evals/run-routing.js
17−```
9+1. **Maximize model performance per task** — raise measured task success of the skills and harness, across frontier SoTA models and smaller/cheaper models alike.
10+2. **Reduce token usage / cost per task** — at equal or better measured performance.
11+ 
12+A change that does neither is noise. A change that trades one goal against the other must say so and show the measurement. Treat every token in a skill description or body as a cost charged against these goals: descriptions are paid on every model invocation, bodies on every skill trigger. Performance claims must name the model class measured; a win on a frontier model that harms a smaller model (or the reverse) is not a proven win.
13+ 
14+## Skill Authoring & Eval Standards
15+ 
16+Distilled from "Don't Ship Skills Without Evals" (Philipp Schmid, Google DeepMind) and "How I deleted 95% of my agent skills and got better results" (Nick Nisi, WorkOS):
17+ 
18+- **Never ship a skill change without eval evidence.** Run the relevant evals on every skill diff; merge only when evals improve or coverage grows. Current post-edit evidence only — historical pre-edit results are context, not proof.
19+- **Measure, don't assume.** More tokens and more instructions do not imply better performance; a loaded skill can actively hurt (documented case: 97% correct without a skill, 77% with it). Trust is a pass rate, not a vibe.
20+- **Run ablations.** Evaluate with and without the skill. Retire a capability skill (one that teaches what the base model can't yet do) when the model matches it unaided — models improve and evals tell you when. Preference skills (this project's conventions) are durable; protect them with regression evals. Keep the eval after retiring the skill as the guard that says when to reintroduce it.
21+- **Guide, don't prescribe.** Skills encode gotchas, landmines, and decision boundaries — not documentation summaries. Reference point: 10,000 generated lines cut to 553 hand-written gotcha lines raised accuracy and cut eval runtime from 68 to 6 minutes.
22+- **Write directives, not essays.** Tell the agent when to use the skill and when not to; keep the required "When NOT to Use" boundary sharp and back it with negative trigger evals.
23+- **Keep skills lean and layered.** Target under 500 words per SKILL.md; push depth into reference files (progressive disclosure). The frontmatter description is the always-paid cost — every word must change routing behavior.
24+- **Kill no-ops.** Delete any instruction that does not change agent behavior ("write clean code", "be thorough"). Every retained line must pay for its tokens.
25+- **Scripts for deterministic work.** If a workflow is always the same, make it a script the agent calls — not prompt content the model re-derives at token cost.
26+- **Enforce, don't instruct.** Put must-happen checks in code — validators, gates, hashes, state machines — not in prose the model can skip or fake. Require verifiable artifacts (output hashes, logs, recorded runs) for claimed results.
27+- **Test outcomes, not paths; test early.** A handful of positive plus negative prompts per skill beats none. Prefer cheap deterministic asserts (regex/exact match) over LLM judges; run multiple trials before trusting a result (agents are non-deterministic); isolate eval runs so agents cannot mine prior state.
28+- **Every failure becomes harness data.** Feed eval failures back into skill gotchas, datasets, or gates — fix the harness, not just the output.
29+ 
30+## Default Workflow
31+ 
32+- Preserve the public skill count at 28 unless a change intentionally adds/removes a shipped skill and updates README, plugin metadata, routing cases, and eval docs together.
33+- Keep skill frontmatter descriptions situation-named and under 200 characters.
34+- Prefer agent-native instructions over human facilitation language.
35+- Add explicit "When NOT to Use" boundaries for every non-router skill.
36+- Do not commit local backups, downloaded third-party datasets, transient logs, or scratch eval runs.
37+ 
38+## Verification
39+ 
40+- Run `node scripts/validate-skills.js` after skill edits.
41+- Run `EVAL_RUN=<name> node evals/run-structural.js` after catalog edits.
42+- Run routing or behavioral evals only when the changed surface warrants the cost.
43+- Use current post-edit evidence only; historical pre-edit results are context, not proof.
44+ 
45+## Local Backups
46+ 
47+Global Claude assets may be backed up under `backups/` for safety. The directory is gitignored. Do not add backup archives to commits.
48+ 
49+## Images
50+ 
51+README and marketing images live in `assets/`. Keep generated source paths out of README links; copy selected assets into the repo and leave generator cache files untouched.
1852  
RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack