bmad-checkpoint-preview

LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%

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

A tight, well-sequenced activation workflow with concrete commands, an explicit failure fallback, and end-of-activation verification. The main gap is progressive disclosure: the body delegates to `./step-01-orientation.md` (and implies further step files via bare-path conventions) but none of those files ship in the bundle, leaving the onward navigation dangling.

Suggestions

Ship the referenced `step-01-orientation.md` (and any subsequent step files implied by the bare-path convention) inside the skill bundle so the one-level-deep reference resolves.

Add a brief one-line note next to the onward reference describing what step-01 covers, so a reader understands the split before following the link.

If step files live under a subdirectory, make the reference path explicit (e.g. `./steps/step-01-orientation.md`) to keep the file layout unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and placeholder-driven (e.g. `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow`) with no padding or explanation of concepts Claude already knows; the detailed merge-rule sentence in Step 1 earns its place as actionable fallback. Not 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	It gives a concrete executable command plus specific file paths and explicit merge rules ("Scalars override, tables deep-merge, arrays of tables keyed by code or id replace matching entries"). Not 2 because the guidance is concrete and copy-paste ready rather than pseudocode or vague direction.	3 / 3
Workflow Clarity	Activation is laid out as six numbered, ordered steps with an explicit error-recovery fallback ("If the script fails, resolve the workflow block yourself ...") and a final checkpoint ("confirm every entry was executed in order ... Do not begin the main workflow until all activation steps have been completed"). Not 2 because validation/checkpoints are explicit, not implicit.	3 / 3
Progressive Disclosure	The body is well-sectioned and signals a single one-level-deep onward reference ("Read fully and follow `./step-01-orientation.md`"), but that referenced file is not present in the skill bundle (no references/, scripts/, assets/, or step file exists), so navigation is broken. Not 3 because the signaled reference target cannot be resolved; not 1 because the structure and signaling are otherwise sound and references are only one level deep.	2 / 3
	Total	11 / 12 Passed

Description

90%

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 well-formed description that clearly pairs a what-statement with an explicit Use-when trigger clause and natural user phrasing. Its only weakness is that the capability verbs ("make sense of", "focus attention", "test") are somewhat abstract rather than enumerating concrete review actions.

Suggestions

Replace abstract verbs with concrete review actions, e.g. "summarize the change, flag risky hunks, suggest test cases to run" so the capability list reads as multiple specific actions.

Consider adding one more natural trigger variation (e.g. "review my change" or "is this change safe to merge") to broaden trigger coverage beyond the three current phrases.

Dimension	Reasoning	Score
Specificity	"Make sense of a change, focus attention where it matters, test" names the review domain and a few actions, but the verbs are abstract ("focus attention where it matters", bare "test") rather than a comprehensive list of concrete actions. Not 3 because it lacks multiple specific concrete actions; not 1 because it does name the domain and several actions.	2 / 3
Completeness	It states what the skill does ("LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test") and gives an explicit when clause ("Use when the user says ..."). Not 2 because the trigger guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	"checkpoint", "human review", and "walk me through this change" are natural phrases a user would actually say when needing this skill. Not 2 because coverage is broad rather than missing common variations.	3 / 3
Distinctiveness Conflict Risk	The checkpoint/human-review-of-a-change niche with these specific triggers is clearly distinguishable and unlikely to fire for unrelated skills. Not 2 because the triggers are distinct rather than broadly overlapping.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: src/bmm-skills/4-implementation/bmad-checkpoint-preview/SKILL.md
Commit: bb45db4

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.