Name: minutes-graph
Rating: 60 (1 reviews)
Author: silverstein

minutes-graph

Policy-safe relationship rankings, commitments, aliases, person profiles, and topic research. Always use Minutes' bounded native CLI surfaces; never build or read a durable graph cache.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/minutes-graph/SKILL.md

The canonical home for this skill is minutes-graph in silverstein/minutes

Quality

Content

78%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 body is highly actionable with exact CLI commands, a well-sequenced workflow with validation checkpoints, and clean single-file organization. Its main weakness is token efficiency: a jargon-heavy opening paragraph and repeated policy refrains could be consolidated without losing any operational guidance.

Suggestions

Trim the opening paragraph to one or two operationally relevant sentences, dropping architecture details (snapshot authority, worker resource limits) that do not change what Claude does.

State the "never fall back to filesystem reads" rule once in the Privacy boundary section and remove the repetitions in Workflow, Output, and Gotchas.

Optionally specify a minimal failure path (e.g. retry once, then report the source unavailable) to close the workflow's missing feedback loop.

Dimension	Reasoning	Score
Conciseness	The opening paragraph pads with architectural jargon ("one supervised, process-private SQLite projection of stable policy-authorized Markdown plus confirmed identity corrections... hard-limited for memory, output, and wall time") that adds little operational value, and "never fall back to filesystem reads" is repeated across Privacy boundary, Workflow, Output, and Gotchas.	3 / 5
Actionability	Five exact, copy-paste-ready commands with correct syntax and placeholders (e.g. "minutes people merge <canonical> <alias...>", "minutes person \"<name>\"") cover all the skill's common cases.	5 / 5
Workflow Clarity	A clear four-step sequence with explicit checkpoints ("Require exit status 0", confirmation gate before the destructive merge) and failure handling ("Report the source unavailable"); it falls short of 5 only because no validate-fix-retry loop is specified for command failures.	4 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references (no references/scripts/assets exist), and is cleanly sectioned into Privacy boundary, Available commands, Workflow, Output, and Gotchas, matching the simple-skill exception.	5 / 5
	Total	17 / 20 Passed

Description

58%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 clearly names a distinct, concrete capability set but omits any explicit "when to use this" trigger guidance, which is its main structural weakness. Trigger terms are domain-relevant yet lack the natural synonyms a user would plausibly say. Third-person voice is maintained and there is no fluff.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about relationship strength, losing touch with someone, person profiles, commitments, or wants topic research grounded in meeting minutes."

Include natural synonyms users would say, such as "losing touch", "contacts", or "who did I meet with", alongside the current capability nouns.

Consider trimming "Always use Minutes' bounded native CLI surfaces; never build or read a durable graph cache" to make room for the trigger clause, since the body already enforces this constraint.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ("relationship rankings, commitments, aliases, person profiles, and topic research") but presents them as noun phrases rather than enumerated actions, leaving minor gaps in coverage.	4 / 5
Completeness	The "what" is clearly stated, but there is no "Use when..." clause or equivalent trigger guidance; the second sentence ("Always use Minutes' bounded native CLI surfaces; never build or read a durable graph cache") is a constraint, not a trigger, which caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like "relationship rankings", "person profiles", and "topic research" are relevant, but common natural variations users would actually say (e.g. "losing touch", "contacts", "who did I meet with") are missing.	3 / 5
Distinctiveness Conflict Risk	Minutes-specific vocabulary and graph-cache language create a clear niche with minimal conflict risk, though the broad phrase "topic research" invites minor overlap with generic research skills.	4 / 5
	Total	14 / 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: silverstein/minutes
Path: .opencode/skills/minutes-graph/SKILL.md
Commit: 5fbe77b

Reviewed: 6 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.