gc-agents

Managing agents — list, peek, nudge, suspend, drain

Quality

67%

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 ./internal/bootstrap/packs/core/skills/gc-agents/SKILL.md

Quality

Content

76%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 token-efficient and highly actionable, organized into clear command-grouped sections. Its main weakness is the absence of validation/verify steps for destructive agent operations, which caps workflow clarity.

Suggestions

Add an explicit verify step for destructive operations, e.g. 'After drain, run `gc runtime drain-check <name>`; only proceed once drained' and 'After `gc session close`, confirm the session is gone with `gc session logs`.'

Move the migration-doc reference into a clearly signaled section (e.g. '## Migration notes') rather than embedding it in the Sessions prose.

Provide example values for placeholders (e.g. `gc session new <template>` → `gc session new worker`) to close the actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is lean: each section is just executable `gc` commands with inline `#` annotations, no preamble explaining what agents or tmux are, so every token earns its place — matching 'lean and efficient; assumes Claude's competence.'	5 / 5
Actionability	Commands are concrete and copy-paste ready with per-line comments, but placeholders like <name>/<template> lack example values and a few behaviors (drain-ack sequencing, GC_AGENT env) are only named, fitting 'mostly executable guidance; minor gaps.'	4 / 5
Workflow Clarity	The destructive/batch operations (suspend, kill, close, drain) have no explicit validation or verification checkpoint, and the judging guidance caps workflow_clarity at 3 when validation is missing for such operations.	3 / 5
Progressive Disclosure	Under 50 lines and cleanly sectioned (Adding, Sessions, Pools, Lifecycle, Runtime) with no nested references, but the single prose pointer to engdocs/archive/migrations/... is buried mid-section rather than clearly signaled, matching 'good structure; minor organization gaps.'	4 / 5
	Total	16 / 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 is concise and lists concrete agent-management actions, but it lacks any explicit 'Use when...' trigger guidance and relies on somewhat jargony verbs. These gaps cap completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when managing Gas City agents — listing, nudging, suspending, or draining workers.'

Broaden trigger terms with natural synonyms like 'agents, worker sessions, runtime drain' so users are more likely to phrase a matching request.

Align the listed actions with the body's command set (e.g. include 'add' and 'logs') to improve coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'list, peek, nudge, suspend, drain' names several concrete agent-management actions, matching the 'lists several specific actions; minor gaps in coverage' anchor; not a 5 because the terse verbs are slightly jargony and a couple of operations (add, resume, undrain, logs) from the body are absent from the description.	4 / 5
Completeness	It clearly states what the skill does but has no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'list, peek, nudge, suspend, drain' are relevant but internal/jargony terms a user would only partially say naturally, and common synonyms (agents, workers, sessions) are missing, fitting 'some relevant keywords but missing common variations.'	3 / 5
Distinctiveness Conflict Risk	'Managing agents' with these specific operations is a mostly distinct niche with only minor overlap risk, matching 'mostly distinct; minor overlap risk with closely related 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: crypt0nerd1/gascity
Path: internal/bootstrap/packs/core/skills/gc-agents/SKILL.md
Commit: f530008

Reviewed: 2 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.