CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mode-classification

Use before routing a /meta-agent request to choose single-agent-creator, team-builder, or agentlas-packager from the user's wording and available files.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/mode-classification/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A tight, well-sequenced decision procedure that gives concrete rules for mode selection, loop policy, and the overlay, with no wasted tokens. The main deductions are the undefined clarify-question loop, decision-critical details deferred to files absent from the bundle, and a small amount of repetition.

Suggestions

Define or inline the clarify question loop (even one line: what to ask and when to stop) instead of referencing it as an undefined mechanism twice.

Ensure the referenced files (docs/mode-classifier.md, modes/ontology-backed-agent.md, .agentlas/contract-injection-map.json) ship in the skill bundle, or inline the essential risk-tier mapping for loop_policy so the guidance is self-contained.

Merge the clarify-loop guidance from steps 3 and 9 into a single rule to remove the repetition.

DimensionReasoningScore

Conciseness

The body is lean and domain-specific throughout — ownership-boundary counting, the shape guard, loop-policy risk tiers — and assumes Claude's competence with no padding or explanation of known concepts. It is not a 5 because of minor trimmable repetition: the clarify question loop is prescribed twice (step 3 'run the clarify question loop before generating' and step 9 'run the clarify question loop instead of guessing').

4 / 5

Actionability

The guidance is concrete and executable for an instruction-only skill: explicit decision rules ('One boundary means single-agent-creator. Two or more boundaries means a team-builder candidate'), a three-item ownership checklist, named overlay file path, and specific loop_policy values ('none', 'self-correct', 'verified'). It is not a 5 because key execution details live in referenced files that are not present in the bundle ('.agentlas/contract-injection-map.json' risk tiers, the clarify question loop definition), leaving concrete gaps.

4 / 5

Workflow Clarity

The nine-step procedure is clearly ordered with explicit checkpoints: an ambiguity feedback loop ('If the boundary count is unclear, run the clarify question loop'), a shape-guard validation step, and an overlay check. It is not a 5 because the clarify question loop — the primary error-recovery mechanism, invoked twice — is never defined or specified in the body, and no destructive/batch validation is needed so the cap does not apply.

4 / 5

Progressive Disclosure

Good structure with well-organized sections (Procedure, Return, Reference) and one-level-deep, clearly signaled references ('See docs/mode-classifier.md', 'modes/ontology-backed-agent.md', '.agentlas/contract-injection-map.json') rather than inlined bulk detail. It is not a 5 because the referenced paths cannot be verified against the bundle — no references/, scripts/, or docs/ files exist — so navigation relies on files that are not demonstrably present.

4 / 5

Total

16

/

20

Passed

Description

71%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.

A compact, third-person description that answers both what and when with a distinct, low-conflict niche. Its main weakness is trigger-term quality: it leans on internal mode names as keywords rather than the natural user phrasings (convert, repair, team, import) that actually signal each mode.

Suggestions

Add natural trigger phrasings users would actually say, e.g. 'Use when the user asks to create an agent, build a team of agents, or convert/repair/import existing agent files' — this would lift trigger_term_quality and completeness.

Mention the core decision signal (independent ownership boundaries / memory, tools, success criteria per role) so the what-clause conveys how the choice is made, not just which modes exist.

Optionally note the ontology-overlay condition (knowledge search over user documents, citation-attached generation) as a trigger users would phrase naturally.

DimensionReasoningScore

Specificity

The description lists several specific actions — 'choose single-agent-creator, team-builder, or agentlas-packager from the user's wording and available files' — naming the domain, the three concrete outcomes, and the inputs used. It falls short of a 5 because it does not convey what distinguishing the modes involves (e.g., ownership boundaries, converting/repairing existing material), leaving minor gaps in coverage.

4 / 5

Completeness

It explicitly answers both parts: 'Use before routing a /meta-agent request' provides an explicit when-clause, and 'to choose single-agent-creator, team-builder, or agentlas-packager from the user's wording and available files' provides the what. Not a 5 because the when-clause is generic — it names no concrete trigger phrasings (e.g., 'team', 'convert', 'repair', 'import') that would tell Claude when this skill fires among similar meta-agent requests.

4 / 5

Trigger Term Quality

It includes relevant keywords ('/meta-agent request', 'routing', 'user's wording', 'available files') but the load-bearing terms are internal skill names (single-agent-creator, team-builder, agentlas-packager) rather than natural user phrasings like 'build a team', 'convert existing agents', or 'repair an agent' that the body itself identifies as signals. Some relevant keywords are present, but common variations and synonyms are missing, matching the 'Some relevant keywords but missing common variations' anchor rather than the good-coverage anchor above.

3 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — mode selection for /meta-agent routing among three named modes — with distinct triggers that would not plausibly fire for unrelated skills. It clearly matches the 'clear niche with distinct triggers; minimal conflict risk' anchor and is more specific than the 'minor overlap risk with closely related skills' anchor at 4.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

agentlas-ai/Agentlas-OS

Path

.agents/skills/mode-classification/SKILL.md

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.