Skill
a11y-check
Accessibility audit, scoped to the surfaces a product actually has. Detects web / rendered_markdown / terminal / native_app / video_audio / document /…
Development
Skill
/prompt-optimizer
A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results.
Install
$ npx -y skills add haabe/mycelium --skill prompt-optimizer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/prompt-optimizer
Context preview
The summary Claude sees to decide when to auto-load this skill.
A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results.
SKILL.md
prompt-optimizer.SKILL.mdname: prompt-optimizer
description: "A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results."
metadata:
instruction_budget: "17"
framework_dependency: "mycelium"
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."
Prompt Optimizer
Systematically improve Mycelium instructions through measurement. Adapted from n-trax.
Commands
`baseline` -- Capture current performance
1. Run `/mycelium:eval-runner run-split optimization` — record as optimization scores 2. Run `/mycelium:eval-runner run-split holdout` — record as holdout scores 3. Record both to `.claude/optimization/baseline.json`: timestamp, CLAUDE.md hash, optimization metrics, holdout metrics, overall and per-category metrics
`test <variant>` -- Test a variant
1. Read variant from `.claude/optimization/variants/<variant>.md` 2. Apply the CLAUDE.md changes described 3. Run `/mycelium:eval-runner run-split optimization` — this is the hill-climbing signal 4. Run `/mycelium:eval-runner run-split holdout` — this validates generalization 5. Store results in `.claude/optimization/results/<variant>.json` 6. Compare against baseline. Flag **overfitting** if optimization improves but holdout degrades. 7. Do NOT auto-revert -- let user decide
`report` -- Compare all variants
Generate comparison table with split-aware columns:
| Variant | Opt Pass Rate | Holdout Pass Rate | Delta Opt | Delta Holdout | Overfit? | Decision |
Flag `Overfit? = YES` when optimization delta is positive but holdout delta is negative.
`exemplar <eval-name>` -- Capture winning trajectory
After a clean eval win (1 iteration, fast), save the approach to `.claude/optimization/exemplars/`.
Workflow
1. Capture baseline 2. Hypothesize an instruction improvement 3. Document in variants/ directory 4. Test the variant 5. Compare via report 6. Keep or revert based on data 7. Capture exemplars from clean wins
Read more
name: prompt-optimizer description: "A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results." metadata: instruction_budget: "17" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."
Prompt Optimizer
Systematically improve Mycelium instructions through measurement. Adapted from n-trax.
Commands
`baseline` -- Capture current performance
1. Run `/mycelium:eval-runner run-split optimization` — record as optimization scores 2. Run `/mycelium:eval-runner run-split holdout` — record as holdout scores 3. Record both to `.claude/optimization/baseline.json`: timestamp, CLAUDE.md hash, optimization metrics, holdout metrics, overall and per-category metrics
`test <variant>` -- Test a variant
1. Read variant from `.claude/optimization/variants/<variant>.md` 2. Apply the CLAUDE.md changes described 3. Run `/mycelium:eval-runner run-split optimization` — this is the hill-climbing signal 4. Run `/mycelium:eval-runner run-split holdout` — this validates generalization 5. Store results in `.claude/optimization/results/<variant>.json` 6. Compare against baseline. Flag **overfitting** if optimization improves but holdout degrades. 7. Do NOT auto-revert -- let user decide
`report` -- Compare all variants
Generate comparison table with split-aware columns:
| Variant | Opt Pass Rate | Holdout Pass Rate | Delta Opt | Delta Holdout | Overfit? | Decision |
Flag `Overfit? = YES` when optimization delta is positive but holdout delta is negative.
`exemplar <eval-name>` -- Capture winning trajectory
After a clean eval win (1 iteration, fast), save the approach to `.claude/optimization/exemplars/`.
Workflow
1. Capture baseline 2. Hypothesize an instruction improvement 3. Document in variants/ directory 4. Test the variant 5. Compare via report 6. Keep or revert based on data 7. Capture exemplars from clean wins
Ships withmycelium
A harness that asks who this is for before the agent writes code. Built on Claude Code, where the gates are structural. The files and skills port to opencode, Codex and Cursor. Outcome over output. You know how this goes.
Get the whole plugin
Other skills on mycelium.
Skill
adopt
Bring Mycelium into a project that already has code. Detects that the repo predates the framework, asks before touching anything, then reads the codebase to…
Skill
assumption-test
Design the smallest viable test to validate or invalidate a critical assumption. Based on Torres's assumption testing framework, organized by Gilad's AFTER…
Skill
bias-check
Use before any research activity or significant decision. Reviews cognitive biases relevant to the current stage.
Skill
bvssh-check
Use to evaluate whether current work aligns with Better Value Sooner Safer Happier. Run at diamond completion and periodically.
Skill
canvas-health
Lint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before major transitions.