bm-checkpoint

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

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

This is a strong instruction-only skill body: every step is concrete and executable, error paths have explicit recovery loops, and nothing explains concepts Claude already knows. The only real improvement is structural — moving the profile frontmatter schemas and the linking procedure into a reference file would shorten the main file while keeping it navigable.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational throughout — it assumes competence (no explanation of git, Basic Memory, or note-taking concepts) and gives exact commands like `git rev-parse --abbrev-ref HEAD`, but has minor trim opportunities: `cwd` is listed both in the common frontmatter and again in the coding-profile fields, and the never-edit-immutability rule is restated several times.	4 / 5
Actionability	Fully executable guidance: exact commands (`git status --short`, `git rev-parse --show-toplevel`, `git rev-parse HEAD`), an exact tool invocation with parameters (`write_note` with `project=`, `overwrite=False`, `output_format="json"`), exact title and resume-command formats, and a concrete precedence order (`permalink`, `file_path`, `title`) for the resume identifier.	5 / 5
Workflow Clarity	The Gather → Write → Confirm sequence is clearly sectioned with explicit validation and recovery loops: title-collision retry with the smallest numeric suffix, treating `action: conflict`/`NOTE_ALREADY_EXISTS` as the collision path, stopping on any other action or error, and stopping when required coding fields cannot be proven.	5 / 5
Progressive Disclosure	The single file is well-sectioned (Gather / Write / Confirm with clear subsections) and references no bundle files, but at ~215 lines it inlines detailed material — the two profile frontmatter schemas and the multi-step same-chat linking procedure — that could live in a one-level-deep reference file to keep SKILL.md as an overview.	4 / 5
	Total	18 / 20 Passed

Description

50%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 concise, concrete, and highly distinctive, but it answers only the "what" — the "when to use this" triggers that would let a model (or user) correctly select this skill live in the body instead of the description. Lifting those trigger phrases into the description would fix both the completeness and trigger-term gaps.

Suggestions

Append an explicit trigger clause to the description, e.g. "Use when the user asks to checkpoint, wrap up, hand off, or remember Codex work state, or when the post-compaction SessionStart context requests a handoff" — this directly mirrors the triggers already written in the body.

Include natural user phrases users would actually say ("checkpoint", "hand off", "wrap up work", "save progress") in the description so trigger matching does not depend on tool-specific jargon like "bm-orient".

Optionally name one more concrete action (e.g. linking the checkpoint to prior same-session checkpoints) to move specificity from two actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (Basic Memory, Codex) and two concrete actions — "Create an immutable Codex handoff in Basic Memory" and "return an exact bm-orient resume command" — but stops at two actions rather than covering the skill's gathering, linking, and confirmation behavior, matching the 1-2-concrete-actions anchor rather than the several-actions anchor.	3 / 5
Completeness	The "what" is clear (create an immutable handoff note and return a resume command), but the "when" is entirely absent — there is no "Use when..." clause or equivalent trigger guidance in the description, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	The description contains only tool-specific jargon ("immutable Codex handoff", "bm-orient resume command") with no natural user phrases; the natural trigger words a user would actually say ("checkpoint", "wrap up", "hand off", "remember the work state") appear only in the body, not the description.	2 / 5
Distinctiveness Conflict Risk	"Codex", "Basic Memory", and "bm-orient" carve out a clear niche with distinct triggers; no other plausible skill would match this combination, so conflict risk is minimal.	5 / 5
	Total	13 / 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: 194afe1

Reviewed: 7 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.