bm-checkpoint

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

Quality

72%

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

77%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.

The body is highly actionable with an explicit, well-validated workflow and concrete tool-call parameters, but it runs long with some redundant emphasis and keeps all detail inline rather than offloading the lengthy schemas/procedures to reference files. Tightening repetition and splitting reference material would improve token efficiency and progressive disclosure.

Suggestions

Consolidate the repeated immutability, non-overwrite, and 'do not infer identity' guidance into a single stated rule to cut redundancy across the Gather and Write sections.

Move the detailed general/coding frontmatter field schemas and the same-chat lineage procedure into a reference file (e.g. references/checkpoint-schema.md) to reduce the monolithic body and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly necessary operational detail, but at ~210 lines it repeats themes (immutability, non-overwrite, 'do not infer', read-only evidence) in several places and could be tightened without losing clarity.	2 / 3
Actionability	Guidance is concrete and executable: exact `write_note` parameters, specific git commands (`git rev-parse --show-toplevel`, `git rev-parse --abbrev-ref HEAD`), exact title format, explicit frontmatter field lists, and a copy-ready resume command.	3 / 3
Workflow Clarity	A clear Gather → Write → Confirm sequence with explicit validation checkpoints (title-collision retry with suffix, `action: created` vs `action: conflict`, 'stop on any other action or error', 'stop if required coding fields cannot be proven', SHA-resolution verification before linking).	3 / 3
Progressive Disclosure	Sections are well organized but the document is a single ~210-line monolith with no external reference files; detailed frontmatter schemas and the same-chat lineage procedure are inline content that could be split out, so it does not meet the under-50-line carve-out for a 3.	2 / 3
	Total	10 / 12 Passed

Description

67%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.

The description is concrete and distinctive, naming two specific actions in a clear niche, but it omits an explicit 'Use when...' trigger clause and leans on technical jargon rather than the natural terms a user would say. Adding trigger guidance with common phrasings would raise completeness and trigger quality.

Suggestions

Append a 'Use when...' clause with natural triggers, e.g. 'Use when the user asks to checkpoint, wrap up, hand off, or remember Codex work state.'

Surface natural keywords ('checkpoint', 'wrap up', 'hand off') in the description itself rather than only the technical phrasing ('immutable handoff', 'bm-orient resume command').

Dimension	Reasoning	Score
Specificity	Names two concrete actions — 'Create an immutable Codex handoff in Basic Memory' and 'return an exact bm-orient resume command' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent trigger guidance; per the rubric a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	'Codex handoff' is a relevant keyword, but the description relies on technical jargon ('immutable', 'bm-orient resume command') and omits the natural variations users actually say ('checkpoint', 'wrap up', 'hand off') that appear only in the body.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Codex handoff in Basic Memory' plus 'bm-orient resume command' carves a clear niche that is unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 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: basicmachines-co/basic-memory
Path: plugins/codex/skills/bm-checkpoint/SKILL.md
Commit: cb95e59

Reviewed: 11 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.