team-executor
Lightweight session execution skill. Resumes existing team-coordinate sessions for pure execution via team-worker agents. No analysis, no role generation -- only loads and executes. Session path required. Triggers on "Team Executor".
64
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex/skills/team-executor/SKILL.mdQuality
Discovery
75%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 functionally complete with clear 'what' and 'when' clauses, explicit exclusions (no analysis, no role generation), and a distinct trigger phrase. Its main weaknesses are that the concrete actions are somewhat vague ('loads and executes' without specifying what) and the trigger terms are highly specialized rather than natural user language. However, given this appears to be an internal/system-level skill triggered by a specific phrase, the specialized terminology may be appropriate.
Suggestions
Specify what is being executed more concretely — e.g., 'executes task plans assigned to team-worker agents' or 'runs queued workflow steps' to improve specificity.
Consider adding natural language trigger variations beyond the exact phrase 'Team Executor', such as 'run team session', 'execute team workflow', or 'resume team execution'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain (session execution via team-worker agents) and some actions (resumes sessions, loads and executes), but the actions are not concretely detailed — 'loads and executes' is vague about what is actually being executed or what outputs are produced. | 2 / 3 |
Completeness | The description answers both 'what' (resumes existing team-coordinate sessions for pure execution via team-worker agents, no analysis, no role generation) and 'when' (triggers on 'Team Executor', session path required). The explicit trigger guidance is present. | 3 / 3 |
Trigger Term Quality | It includes the explicit trigger phrase 'Team Executor' and mentions 'session execution' and 'team-worker agents', but these are specialized/internal terms rather than natural keywords a user would commonly say. Missing common variations or natural language triggers. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a very specific niche — it explicitly excludes analysis and role generation, requires a session path, and has a distinct trigger phrase 'Team Executor'. This makes it clearly distinguishable from other skills and unlikely to conflict. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured execution skill with strong actionability — concrete spawn templates, timeout escalation patterns, and state reconciliation logic are all clearly specified. Workflow clarity is excellent with explicit validation gates and phased execution. The main weaknesses are moderate verbosity from redundant sections (dispatch table repeating validation) and inline content that could benefit from progressive disclosure to referenced files, especially given that referenced files like roles/executor/role.md and specs/session-schema.md are not provided in the bundle.
Suggestions
Remove the Role Router dispatch logic table which largely duplicates the Session Validation section, or merge them into a single flow
Provide the referenced bundle files (roles/executor/role.md, specs/session-schema.md) or note them as expected session artifacts to improve progressive disclosure scoring
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy — the dispatch logic table largely repeats the validation section, and the architecture ASCII diagram adds little value. Some sections like the integration table and model selection guide are useful but could be tighter. | 2 / 3 |
Actionability | Provides concrete, executable spawn_agent templates with exact parameter structures, specific wait/timeout patterns, state reconciliation code snippets, and precise completion action handlers with request_user_input calls. The error handling table gives specific resolution steps for each failure mode. | 3 / 3 |
Workflow Clarity | The lifecycle is clearly sequenced (Phase 0 reconcile -> Phase 1 spawn -> worker callback -> advance -> Phase 2 report). Validation is explicitly gated before execution, timeout handling has a clear escalation path (STATUS_CHECK -> FINALIZE -> mark timed_out -> close), and state reconciliation on resume provides error recovery. | 3 / 3 |
Progressive Disclosure | References roles/executor/role.md and specs/session-schema.md but no bundle files are provided to verify these exist. The skill keeps most content inline rather than splitting detailed sections (like the spawn template or completion actions) into referenced files, making it somewhat monolithic for its length. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
5ff5e86
- Reviewed
Table of Contents
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.