CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

plannotator-inbox

Open the Plannotator Inbox in the browser (starting it if needed), say its address, and learn how to use the Inbox for the rest of the session.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./apps/skills/claude/plannotator-inbox/SKILL.md
SKILL.md
Quality
Evals
Security

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.

This is a lean, instruction-only skill that scores well: every command and tool reference is concrete, the single-purpose task is unambiguous with explicit error handling, and structure is clean with details correctly deferred to --help and a companion skill. The only minor room for improvement is showing a literal send_message example and sequencing the usage rules more linearly.

DimensionReasoningScore

Conciseness

The body is dense and operational — commands, tool names, and error strings rather than concept explanations — with only minor padding such as "proactivity is better than procrastination" and the slightly redundant restatement of non-blocking sends. It fits 'efficient; minor instances of over-explanation that could be trimmed'; not 5 because a few sentences could be tightened without losing meaning.

4 / 5

Actionability

Concrete, executable guidance throughout: `plannotator inbox --open`, `plannotator inbox --help`, `plannotator update`, `plannotator inbox mcp`, and "send_message ... `action` `send_message`, with a markdown `body`", plus explicit error handling ("`Unknown inbox option: --open` means their Plannotator is older"). It falls short of anchor 5 only because no copy-paste send_message example payload is shown; well above anchor 3 since everything given is directly runnable.

4 / 5

Workflow Clarity

'Your task' gives a clear sequence — read the command output, tell the address in one sentence, handle the error case with its specific message, then stop — which is a simple single-purpose task with an explicit error-recovery branch. Not 5 because the Inbox usage rules (when to send, how, and the non-blocking protocol) are spread across bullets rather than a sequenced send-then-respond flow; comfortably above 3 since checkpoints and error recovery are present.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external reference files, and the content is well organized into 'Inbox address', 'Using the Inbox', and 'Your task' sections. Deep material is appropriately deferred one level to `plannotator inbox --help` and the separate `plannotator` skill, so the simple-skill exception applies and the structure matches anchor 5.

5 / 5

Total

17

/

20

Passed

Description

62%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 specific and highly distinctive thanks to the unique product name, with clearly stated actions in third-person imperative voice. Its main weakness is the absence of any 'when to use' trigger guidance or natural-language variations, which caps both completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the person asks to open or use the Plannotator Inbox, or when a session needs the Inbox for messages and decisions.'

Include natural variations of the trigger terms users might say, such as 'inbox', 'message window', or 'ask me in the Inbox', to improve keyword coverage.

Briefly enumerate what 'learn how to use the Inbox' covers (leaving messages, :::question blocks, files) to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Quotes three concrete actions — "Open the Plannotator Inbox in the browser (starting it if needed)", "say its address", "learn how to use the Inbox" — matching the 'several specific actions; minor gaps' anchor. Not 5 because coverage of what 'learning to use it' involves is not enumerated; not 3 because more than 1-2 concrete actions are explicitly stated.

4 / 5

Completeness

The 'what' is clear (open, start if needed, say the address, learn usage) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

"Plannotator Inbox", "browser", and "address" are relevant keywords, but the description includes no natural variations or synonyms a user might say (e.g. 'inbox', 'message window', 'open the inbox'), matching the 'some relevant keywords but missing common variations' anchor. It is above 2 because the product name itself is exactly what a user would say; below 4 because no broader phrasing is present.

3 / 5

Distinctiveness Conflict Risk

"Plannotator Inbox" names a unique, specific tool and window, giving it a clear niche with minimal risk of triggering for the wrong skill — a direct match to the anchor-5 example's structure. Even the anchor-4 'minor overlap risk' does not apply since no generic capability terms are used.

5 / 5

Total

15

/

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

backnotprop/plannotator

Path

apps/skills/claude/plannotator-inbox/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.