Tessl • The management layer for AI agent skills

The SKILL.md body is an exemplary lean instruction file: concrete copy-paste commands, explicit constraints and fallback behavior, tight rules with tradeoffs, and a single well-placed reference file for examples. The only notable gap is the absence of an explicit verify-after-set checkpoint in the main workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout: rules are one line each ("Diagnose before explaining.", "Don't check every turn. Costs a tool call."), commands live in compact tables, and the closing "Tomorrow? Memory. This turn only? My." is maximal signal per token. Nothing explains concepts Claude already knows, matching 'lean and efficient; every token earns its place'.	5 / 5
Actionability	Concrete copy-paste-ready commands with real keys and values are given, e.g. `my(action="check", key="context_window_tokens")`, `my(action="set", key="model_preset", value="<preset-name>")`, and `my(action="set", key="max_iterations", value=80)`, covering the common check/set cases. Validated ranges ("max_iterations (1–100)") and the fallback "If tools.my.allow_set is false, check only" add the missing-detail-free specificity of a 5.	5 / 5
Workflow Clarity	The 'How to use' sequence (identify situation → call my tool → warn user before impactful sets → read examples for detail) is clear and includes a pre-set warning checkpoint plus failure-mode handling (rejected direct model writes, allow_set false), matching 'clear sequence with most checkpoints present'. It is not a 5 because there is no explicit post-set verification step (e.g. re-check the key or confirm the preset took effect) in the body.	4 / 5
Progressive Disclosure	The ~70-line body is well-sectioned (When to check, When to set, Anti-patterns, Constraints, Related tools) and pushes detailed examples to a single, clearly signaled, one-level-deep reference: "For detailed examples, read [references/examples.md](references/examples.md)" — the file exists in the bundle with no further nesting. This matches 'clear overview with well-signaled one-level-deep references'.	5 / 5
	Total	19 / 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, third-person, and names three concrete capabilities, but it lacks any explicit 'when to use' trigger guidance and omits the natural phrases a user would say when needing this skill. It is functional but would be missed in situations where users ask about model, limits, or session memory in everyday language.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks what model/limits you are running, why you stopped, wants you to remember something for this session, or asks you to switch model presets or raise iteration limits."

Include natural synonyms such as "scratchpad", "session notes", "model preset", "context window", and "iteration limit" so the description matches how users actually phrase these requests.

Mention 1-2 concrete operations like checking the context window or switching model presets to sharpen the 'what' toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Inspect or troubleshoot the agent's runtime state, adjust runtime settings, or keep temporary session notes" lists three concrete action areas in third person, matching 'lists several specific actions; minor gaps in coverage'. It is not a 5 because it omits specifics like checking budget/limits, switching models, or scratchpad read-back, which the body and examples actually cover.	4 / 5
Completeness	The 'what' is clear (inspect/troubleshoot state, adjust settings, keep session notes) but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by "troubleshoot" — which caps completeness at 3 per the judging guidelines. It does not merit 4 because the when is not merely under-specified, it is absent.	3 / 5
Trigger Term Quality	Terms like "runtime state", "troubleshoot", "runtime settings", and "temporary session notes" are relevant but miss the natural phrases users would actually say ("what model are you running", "why did you stop", "check your limits", "remember this for this session", "scratchpad"), matching 'some relevant keywords but missing common variations or synonyms'. Keyword coverage is not good enough for 4.	3 / 5
Distinctiveness Conflict Risk	"agent's runtime state" and "runtime settings" carve out a clear self-inspection niche with mostly distinct triggers, matching 'mostly distinct; minor overlap risk'. Minor overlap exists with the memory skill via "keep temporary session notes", keeping it below 5.	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: HKUDS/nanobot
Path: nanobot/skills/my/SKILL.md
Revision: 9adbcc2

Reviewed: 3 days ago

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.

my

Table of Contents

Is this your skill?