CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

darwinian-evolver

Evolve prompts/regex/SQL/code with Imbue's evolution loop.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/research/darwinian-evolver/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill: executable install/verify/smoke-test commands, exact API signatures, a defaults table, and a pitfalls section capturing genuinely non-obvious failure modes. The one real defect is a broken bundle reference — the promised `templates/custom_problem_template.py` does not exist.

Suggestions

Ship the missing `templates/custom_problem_template.py` (or repoint the 'Defining a Custom Problem' section to copy `scripts/parrot_openrouter.py` as the template), so the 'copy, edit, run' instruction doesn't dead-end.

Trim the 'Status: thin wrapper' paragraph and the cost aside ('On gpt-4o-mini that's pennies; on Claude Sonnet it can be a few dollars') to a single budget line to tighten token efficiency.

Move the expected parrot scores ('best landing around 0.6–0.8') next to the verification command so validation has a concrete success criterion inline.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational knowledge (nested pickles, hardcoded Anthropic CLI, AGPL boundary, concurrency defaults) and assumes Claude's competence, e.g. "**`loop.run()` is a generator** — calling it doesn't run anything until you iterate." Minor trimming is possible in the 'Status: thin wrapper' paragraph and the cost narrative ('pennies' / 'a few dollars'), which keeps it below the lean-everything-earns-its-place anchor.

4 / 5

Actionability

Nearly everything is copy-paste executable: install block, 'Verify:' command, the parrot smoke test, the OpenRouter driver invocation with expected output ('7 evolved prompt templates ranked by score... best landing around 0.6–0.8'), and a hyperparameter table with defaults and when to change. The gap: 'The skill ships `templates/custom_problem_template.py` — copy, edit, run' references a file that does not exist in the bundle, leaving the custom-problem path without the promised starting artifact.

4 / 5

Workflow Clarity

The sequence is explicit and gated: prerequisites → Install with a Verify command → parrot smoke test → 'Defining a Custom Problem' (three numbered component definitions with exact signatures, e.g. '`.evaluate(organism) -> EvaluationResult(score=..., trainable_failure_cases=[...], ...)`') → hyperparameters → pitfalls. Explicit validation checkpoints appear both after install and in a dedicated '## Verification' section ('exit code 0 from this is sufficient'), and Pitfall 2 provides an error-recovery pattern (wrap in try/except, return `f"<LLM_ERROR: {e}>"`).

5 / 5

Progressive Disclosure

Good structure with well-signaled, one-level-deep references to real bundle files: 'the skill ships `scripts/parrot_openrouter.py`' and 'Inspect the result with `scripts/show_snapshot.py`' both exist and behave as described, and the driver is explicitly named as 'the reference' for custom problems. However, the referenced `templates/custom_problem_template.py` is absent from the bundle (no templates/ directory), so one referenced path is a dead end — a minor organization gap that keeps this below the top anchor.

4 / 5

Total

17

/

20

Passed

Description

61%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, concrete description that clearly states what the skill does and names a distinct mechanism, but it omits any 'when to use' trigger guidance and the most common user phrasings ('optimize', 'improve'). Adding a Use-when clause with those synonyms would move it to the top anchors.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user says "optimize this prompt", "evolve a regex", or "auto-improve this SQL/code" and a measurable scorer exists.'

Add the common synonyms users actually say — 'optimize', 'improve', 'auto-improve' — since the body's When-to-Use section already quotes these phrasings.

Optionally note the scale/cost signal ('requires a fitness function; 50–500 LLM calls') to further sharpen distinctiveness from cheap one-shot editing skills.

DimensionReasoningScore

Specificity

The description names the domain concretely — 'Evolve prompts/regex/SQL/code' — and gives one concrete action ('Evolve ... with Imbue's evolution loop'), matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive.' It is not a 4 because only one action verb is offered (no optimize/improve/tune equivalents), and not a 2 because the enumerated target list and named mechanism are far more concrete than 'Processes PDF files'.

3 / 5

Completeness

The 'what' is clear ('Evolve prompts/regex/SQL/code with Imbue's evolution loop') but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description — the body's rich When-to-Use section is not reflected. Per the judging guideline, a missing 'Use when...' clause caps completeness at 3, matching 'Has a clear what but when is missing.'

3 / 5

Trigger Term Quality

Good keyword coverage with a few natural terms missing: 'evolve', 'prompts', 'regex', 'SQL', and 'code' are phrases users would plausibly say ('evolve a regex for X', per the skill's own When-to-Use examples). It misses the common synonyms 'optimize', 'improve', or 'auto-improve' that the body itself quotes users saying, which fits 'Good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of the top anchor.

4 / 5

Distinctiveness Conflict Risk

'Imbue's evolution loop' names a specific niche mechanism, making this mostly distinct from generic prompt-engineering or SQL-tuning skills — fitting 'Mostly distinct; minor overlap risk.' It is not a 5 because the broad targets ('prompts', 'code') and the absence of distinct trigger phrases leave minor overlap risk with closely related optimization skills (e.g. DSPy-style prompt tuning mentioned in the body).

4 / 5

Total

14

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/research/darwinian-evolver/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.