CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad-eval

Runs the evals of a BMad skill through the agent harness the user works in and reports what they show: baseline against the bare model, variant against a stripped or prior version, quality against a rubric, and trigger accuracy of the description with an optional optimization loop. Use when the user asks to evaluate, benchmark, test the triggers of, grade, or compare versions of a skill, or when the bmad-toolsmith skill asks for an eval of a skill it built.

Quality

95%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

The SKILL.md body is an exemplary lean orchestration overview: concrete commands with flags and exit-code semantics, a numbered activation sequence with explicit halt-on-failure checkpoints, error-handling rules for grading, and clean one-level-deep disclosure into five references and five scripts that all exist. No dimension shows a meaningful weakness.

DimensionReasoningScore

Conciseness

The ~60-line body is dense and operational throughout — no concept explanations Claude already knows, no padding; even rationale is compressed to single clauses ("a temporary folder outside the project... so host config, prior runs, the project's instruction files and its installed skills cannot bias the result"). Every token earns its place, matching the score-5 anchor; there are no 'minor instances of over-explanation' that would justify a 4.

5 / 5

Actionability

Guidance is fully executable: two copy-paste command blocks with all flags (`--cases`, `--skill-path`, `--mode quality|baseline|variant`, `--variant-path`, `--runs N`), concrete resolve_config.py/resolve_customization.py invocations, exit-code semantics ("Exit 0 is a complete run; 1 means a case errored or timed out... 3 that no harness is recorded"), and default/threshold values ("--runs defaults to 1... settled only at 3 or more"). This matches the score-5 anchor of copy-paste ready commands covering the common cases.

5 / 5

Workflow Clarity

The 'On activation' section is a numbered 5-step sequence with explicit validation checkpoints and halt conditions ("Verify `<skill-path>/SKILL.md` exists; halt with a clear error if not"; "If nothing is found, halt and say so"), error recovery is specified ("If a grader errors, mark the case `grading_error`, never a default verdict"; exit-code taxonomy), and feedback loops exist for both weak runs (follow `references/self-improvement.md`) and lost baselines ("points to retiring the skill, not patching it"). Batch eval operations have their validation present, so the destructive/batch cap does not apply; this matches the score-5 anchor.

5 / 5

Progressive Disclosure

The body is a lean overview with a modes table that maps each mode to exactly the file that handles it, and all referenced bundle files exist (`references/eval-format.md`, `grader.md`, `harness.md`, `description-optimization.md`, `self-improvement.md`; `scripts/run_evals.py`, `run_triggers.py`, `aggregate_benchmark.py`, `convert_cases.py`). References are one level deep with no nested 'see X for the actual instructions' chains, and bulk detail (case taxonomy, grader protocol, harness facts) is correctly deferred to those files — matching the score-5 anchor of a clear overview with well-signaled one-level-deep references.

5 / 5

Total

20

/

20

Passed

Description

88%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 strong description that clearly states what the skill does across all four eval modes and gives an explicit, well-phrased 'Use when...' clause covering user and programmatic triggers. The only weaknesses are minor: a few natural trigger synonyms are absent and the common trigger verbs have slight overlap risk with generic testing/grading requests.

Suggestions

Add natural trigger synonyms such as 'run the evals for', 'assess', or 'score a skill' to widen the natural-phrases users might say when they need this skill.

Sharpen distinctiveness by making the object unmistakable in every trigger verb, e.g., 'evaluate or benchmark *a skill's performance*' so generic 'grade this' or 'test this' requests for non-skill targets don't fire it.

Consider mentioning the eval artifacts (e.g., a per-run report) in the 'what' clause so users searching for 'run report' or 'eval results' can also find the skill.

DimensionReasoningScore

Specificity

The description enumerates the full capability set concretely: "Runs the evals of a BMad skill through the agent harness the user works in and reports what they show: baseline against the bare model, variant against a stripped or prior version, quality against a rubric, and trigger accuracy of the description with an optional optimization loop." These are multiple specific concrete actions matching the skill's four modes with comprehensive coverage, matching the score-5 anchor; it is not score 4 because there is no notable gap in the action list.

5 / 5

Completeness

It explicitly answers both questions: what ("Runs the evals of a BMad skill through the agent harness... baseline... variant... quality... trigger accuracy") and when ("Use when the user asks to evaluate, benchmark, test the triggers of, grade, or compare versions of a skill, or when the bmad-toolsmith skill asks for an eval of a skill it built") with concrete trigger phrases, matching the score-5 anchor exactly; score 4 would require the 'when' clause to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Trigger terms "evaluate, benchmark, test the triggers of, grade, or compare versions of a skill" are natural phrases a user would say, giving good keyword coverage. It is not 5 because common variations are missing — e.g., "run the evals/tests on a skill", "assess", or "score a skill" — while exceeding the 3 anchor's 'some relevant keywords but missing common variations'.

4 / 5

Distinctiveness Conflict Risk

The niche (evaluating BMad skills specifically) is clear and triggers are qualified by "of a skill", plus a distinct programmatic trigger from bmad-toolsmith, so it is mostly distinct. It is not 5 because broad verbs like "evaluate", "benchmark" and "grade" carry minor overlap risk with closely related testing/grading skills — e.g., a user asking to 'test my skill' meaning unit-test its scripts — fitting the score-4 anchor; it is well above anchor 3's 'could still overlap with similar skills'.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

bmad-code-org/BMAD-METHOD

Path

skills/bmad-eval/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.