CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad-retrospective

Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket's story file and plan, diffs, commits — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when the user says "run a retrospective" or "lets retro the epic [epic]". Supports -H/--headless

Quality

94%

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

96%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 body is a minimal, fully executable launcher: one command with defined substitutions and explicit handling for every outcome branch, with zero wasted tokens. Its only structural weakness is that the overview never surfaces the bundle's reference files, leaving navigation entirely to the render script's output.

DimensionReasoningScore

Conciseness

The body is 13 lines with zero padding and no explanations of concepts Claude already knows — every line instructs ("Run the following command exactly once without changing the current working directory", "On any other output or failure, including `uv` being unavailable, report the command output and stop"). Matches the 5 anchor ('every token earns its place'). Not 4: there is nothing that could be trimmed.

5 / 5

Actionability

A fully executable command is given verbatim — `uv run --no-cache "{project-root}/_bmad/scripts/render_skill.py" --project-root "{project-root}" --skill "{skill-root}"` — with explicit substitution rules ("Replace `{project-root}` with the nearest folder containing `_bmad/`, from the working directory upward") and branches covering the common failure cases (script missing, HALT, uv unavailable). Not 4: the only placeholders are explicitly defined, leaving no gaps between this and copy-paste-ready.

5 / 5

Workflow Clarity

A single unambiguous action with exhaustive outcome handling: success ("The command prints the skill's workflow: follow it"), halt ("`HALT: <reason>`: report the reason and stop"), missing script ("Offer to set it up using `bmad` skill, then run the command again"), and other failures ("report the command output and stop. Do not run any workflow source directly"). Per the simple-skill note, a single unambiguous action with explicit branch directives merits 5; the operation is non-destructive and non-batch, so the validation cap does not apply. Not 4: every outcome branch has an explicit directive — no checkpoints are left implicit.

5 / 5

Progressive Disclosure

Scored against the actual bundle: the content is appropriately split one level deep (5 phase docs in references/ — acceptance-verdict, aggregate-views, evidence-gathering, retro-document, team-discussion — plus scripts/git_evidence.py and its tests), stitched by the render script via one-level `{{ rendered(...) }}` inlines rather than nested link chains. However, the body itself signals none of these files — a reader of SKILL.md alone cannot see the skill's shape without running the renderer. Not 5: the references are not 'well-signaled' from the overview; not 3: nothing is inlined that belongs in a separate file, and navigation via the rendered workflow is one level deep.

4 / 5

Total

19

/

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: concrete actions with enumerated evidence sources and named outputs, plus an explicit 'Use when' clause with quoted trigger phrases. The two 4s reflect keyword coverage that misses common synonyms (post-mortem, lessons learned) and a generic-sounding 'run a retrospective' trigger that carries minor overlap risk with non-epic retrospective skills.

Suggestions

Add natural trigger synonyms to the Use-when clause (e.g. "post-mortem", "lessons learned", "what went well") to broaden keyword coverage toward the 5 anchor.

Qualify the generic trigger phrase — e.g. "run a retrospective on the epic" — so the skill is less likely to fire for generic retrospective or team-meeting requests.

DimensionReasoningScore

Specificity

Quotes: "Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket's story file and plan, diffs, commits", "produce a retrospective with sourced findings, action items, and an acceptance decision", "Supports -H/--headless". Multiple concrete actions (review against enumerated evidence sources; three named outputs; a headless mode) comprehensively cover the skill's scope. Not 4: the action list leaves no minor gaps — inputs, outputs, and operating mode are all explicit.

5 / 5

Completeness

Explicit what: "Review a finished epic folder ... and produce a retrospective with sourced findings, action items, and an acceptance decision." Explicit when with concrete trigger phrases: "Use when the user says 'run a retrospective' or 'lets retro the epic [epic]'". This matches the 5 anchor exactly. Not 4: the when-clause is fully explicit with quoted user phrasing, not merely present-but-improvable.

5 / 5

Trigger Term Quality

Quotes: "Use when the user says \"run a retrospective\" or \"lets retro the epic [epic]\"", plus the natural terms "retrospective" and "retro". These are exactly the phrases a user would say, but coverage stops there. Not 5 (the 5 anchor requires comprehensive synonyms/extensions — e.g. "post-mortem", "lessons learned" are absent); not 3: the quoted phrases go well beyond merely "some relevant keywords".

4 / 5

Distinctiveness Conflict Risk

Quotes: "epic folder in the ticket tree", "each ticket's story file and plan", "acceptance decision", "lets retro the epic [epic]" — strong anchoring to the ticket-tree/BMad domain with distinct triggers. Not 5: the bare trigger "run a retrospective" could also match a generic retrospective or meeting-notes skill, so minor overlap risk remains; not 3: the domain anchoring clearly prevents broad overlap.

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-retrospective/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.