CtrlK
BlogDocsLog inGet started
Tessl Logo

bm-checkpoint

Save a deliberate work checkpoint to Basic Memory with the story, changed files, verification, decisions, blockers, and the next action. Use when the user asks to checkpoint, wrap up, hand off, or remember the state of the work.

79

Quality

100%

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 1-3

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

An instruction-only skill that is dense with executable specifics — exact fields, commands, tags, and validation guardrails — organized into a clear three-phase workflow with no padding. It assumes Claude's intelligence throughout and stays within a single well-structured file with no need for bundle references.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence — it never explains what Basic Memory or git is — and every section earns its place with concrete config keys, exact frontmatter fields, and explicit commands rather than padded prose, matching the lean/efficient anchor; it is not 2 because there is no unnecessary concept explanation or filler to tighten.

3 / 3

Actionability

Guidance is fully executable: exact tags (["claude","checkpoint"]), exact note_type values, exact commands (git rev-parse HEAD, gh pr view --json), exact observation categories ([result]/[decision]/[blocker]/[next_step]), and a typed PR-number convention ("123"); this matches the copy-paste-ready anchor and exceeds the incomplete/pseudocode anchor at 2.

3 / 3

Workflow Clarity

A clear Gather -> Write -> Confirm sequence is reinforced with explicit validation guardrails — "Do not claim a test passed unless you ran it", "Stop if the required coding fields cannot be proven", and omitting PR fields when none exists — matching the anchor for explicit validation steps and feedback on error conditions; it is not 2 because checkpoints are stated, not merely implied.

3 / 3

Progressive Disclosure

No bundle files exist, so per the rubric's simple-skill guidance a single well-organized SKILL.md with clear sections can score 3; the Gather/Write/Confirm structure is clean and the only external pointers (bm-writing skill, write_note tool) are one level deep and clearly signaled.

3 / 3

Total

12

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 precise, third-person description that names concrete checkpoint contents and pairs them with explicit natural-language triggers for both what and when. It is distinctive and free of fluff or over-claims.

DimensionReasoningScore

Specificity

Names multiple concrete checkpoint components — "the story, changed files, verification, decisions, blockers, and the next action" — matching the anchor for listing several specific concrete actions; it is not below 3 because nothing is vague, and the imperative "Save" reads as third-person voice so no specificity penalty applies.

3 / 3

Completeness

It explicitly answers both what ("Save a deliberate work checkpoint to Basic Memory...") and when ("Use when the user asks to checkpoint, wrap up, hand off, or remember the state of the work"), the exact anchor for full completeness; it is not 2 because the 'when' clause is explicit, not implied.

3 / 3

Trigger Term Quality

"checkpoint, wrap up, hand off, or remember the state of the work" are natural phrases a user would actually say, giving good coverage of common variations rather than the single-term anchor at 2.

3 / 3

Distinctiveness Conflict Risk

The Basic Memory niche plus the distinctive trigger set (checkpoint/wrap-up/handoff/remember-state) make it unlikely to fire for the wrong skill, matching the clear-niche anchor; it is not 2 because the domain is specific rather than broadly overlapping.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
basicmachines-co/basic-memory
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.