bm-checkpoint

Create an immutable Codex handoff in Basic Memory and return an exact bm-orient resume command.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/codex/skills/bm-checkpoint/SKILL.md

Quality

Content

88%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 content is a tight, highly actionable procedural workflow with strong validation checkpoints and feedback loops for a fragile immutable-write operation. It is well structured and self-contained; the only mild gap is conciseness (some cautionary repetition) and the absence of any progressive-disclosure split, which is appropriate for this procedural skill but keeps it off the top anchor.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no exposition of git, Basic Memory, or what a handoff is) and is densely operational, but the long evidence-gathering bullet list and repeated cautionary restatements ("never infer...", "do not...") could be trimmed, placing it just below the lean 5 anchor.	4 / 5
Actionability	It gives exact executable commands (git status --short, git rev-parse --show-toplevel/HEAD), a concrete write_note invocation with pinned arguments (overwrite=False, output_format="json"), exact title and resume-command formats, and an ordered resume-identifier fallback (permalink, file_path, title) — fully executable and copy-paste ready for the common cases.	5 / 5
Workflow Clarity	The Gather → Write → Confirm sequence carries explicit validation checkpoints and feedback loops: collision retry with a numeric suffix, accept only action: created / stop on conflict or NOTE_ALREADY_EXISTS, stop if coding fields cannot be proven, and SHA verification before linking a commit, matching the 5 anchor.	5 / 5
Progressive Disclosure	Sections (Gather, Write, Link Checkpoints, Confirm) are clearly headed and the external bm-writing skill reference is one level deep and well signaled, but the skill is a ~200-line monolithic procedural doc with no split reference materials, so it sits at the 4 anchor rather than the overview-pointing-to-deep-references 5.	4 / 5
	Total	18 / 20 Passed

Description

62%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.

The description is specific and highly distinct, naming a clear niche and two concrete actions. Its main weakness is the missing explicit trigger guidance: no "Use when..." clause, so the "when" is only weakly implied and common synonyms (checkpoint, wrap up) are absent.

Suggestions

Add an explicit "Use when..." clause naming trigger phrases users actually say — e.g. "Use when the user asks to checkpoint, wrap up, hand off, or remember Codex work state" — to lift completeness above 3.

Fold in natural synonyms ("checkpoint", "wrap up") alongside "handoff" so trigger term coverage reaches the common variations users voice.

Optionally surface the second concrete action (resumption via bm-orient) more prominently as a paired capability so the "what" reads as comprehensive rather than two discrete actions.

Dimension	Reasoning	Score
Specificity	"Create an immutable Codex handoff in Basic Memory and return an exact bm-orient resume command" names the domain and two precisely modified concrete actions (immutable handoff, exact resume command); it falls just below the 5 anchor because coverage is not comprehensive (gathering evidence, writing the note).	4 / 5
Completeness	The description gives a clear "what" but no "Use when..." clause or explicit trigger guidance, so completeness is capped at 3 per the rubric guideline; the "when" lives only in the body, not the description.	3 / 5
Trigger Term Quality	It surfaces relevant terms ("Codex handoff", "Basic Memory", "bm-orient resume command") but omits the natural user phrasings the body itself lists ("checkpoint", "wrap up", "remember the work state"), matching the anchor with some relevant keywords but missing common synonyms.	3 / 5
Distinctiveness Conflict Risk	The intersection of Codex, Basic Memory, and bm-orient is a clear niche with distinct triggers and minimal overlap with other skills, matching the 5 anchor.	5 / 5
	Total	15 / 20 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: basicmachines-co/basic-memory
Path: plugins/codex/skills/bm-checkpoint/SKILL.md
Commit: a5fb68e

Reviewed: 3 days 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.