CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

egghead-slack

Operate the private egghead Slack integration without leaking workspace data. Covers passive monitoring, explicit ShitRat work triggers, and approval-bound thread replies.

Quality

77%

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 ./skills/egghead-slack/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 an exemplary lean, actionable operating contract: concrete CLI commands, explicit fail-closed rules, and clear boundaries with essentially zero wasted tokens. Minor gaps are the un-shown credential-leasing/backfill commands and the lack of a verification step in the batch backfill workflow.

DimensionReasoningScore

Conciseness

The body is a lean operating contract: every section carries operational rules Claude does not already know (e.g. "Workers return evidence to the gateway. Workers do not post directly.") with no filler, no concept explanations, and no padding. Not 4 because there are no instances of over-explanation that could be trimmed.

5 / 5

Actionability

Concrete, executable commands are given ("jc-slack search '<query>' --channel <channel-name>", "jc-slack reply '<message-permalink>' --text-file <path>") plus exact trigger conditions, event names, and fictional fixtures. Not 5 because the credential-leasing mechanism and backfill procedure are described only in prose without runnable commands; not 3 because the shown commands are complete and executable.

4 / 5

Workflow Clarity

The reply flow and ShitRat trigger have clear sequences with explicit checkpoints (approval-bound confirmation command, fail-closed unmapped-channel behavior, delivery receipts, ":white_check_mark:" after the final result). Not 5 because the batch backfill section ("Backfills paginate channel history, expand active threads...") has no verification step; not 3 because the primary workflows do include validation checkpoints.

4 / 5

Progressive Disclosure

A single well-organized file with clear sections (Boundaries, Credentials, Read workflow, ShitRat work trigger, Approval-bound replies, Backfill, Public fixtures) and one-level-deep pointers ("skills/slack-link/SKILL.md", gateway source paths); no bundle files exist to split content into. Not 5 because the body exceeds 50 lines and dense sections like the ShitRat trigger paragraph could arguably live in a separate reference if a bundle existed.

4 / 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, clearly scoping a private integration with a privacy boundary, but it omits any "when to use" trigger guidance and leans on internal jargon ("ShitRat") that a user would not naturally say. It reads as a capability summary rather than an invocable trigger.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when reading, searching, or replying in egghead Slack channels, or when a :shitrat: activation appears." — the missing trigger clause currently caps completeness at 3.

Replace or gloss internal jargon with natural user phrasing: add terms like "Slack messages", "channels", "thread replies", and "Slack search" so trigger-term coverage includes what users actually say.

Mention the remaining capabilities (channel search/context retrieval, history backfill) so the action list is comprehensive rather than partial.

DimensionReasoningScore

Specificity

"Covers passive monitoring, explicit ShitRat work triggers, and approval-bound thread replies" lists several concrete actions, but coverage has minor gaps (read/search workflows and backfill are unmentioned) and "ShitRat work triggers" is only concrete to insiders. Not 5 because the action list is not comprehensive; not 3 because it goes beyond 1-2 actions in a named domain.

4 / 5

Completeness

The "what" is clear ("Operate the private egghead Slack integration... Covers passive monitoring, ... triggers, and ... replies"), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric. Not 4 because the "when" is not even weakly explicit.

3 / 5

Trigger Term Quality

"Slack" and "thread replies" are natural terms, but "explicit ShitRat work triggers" is private jargon and common user phrasings ("Slack messages", "channels", "reply in a thread") are absent. Not 4 because a natural trigger phrase a user would actually say is largely missing; not 2 because the domain keyword is present and correct.

3 / 5

Distinctiveness Conflict Risk

"private egghead Slack integration" carves out a clear niche with distinct, workspace-specific triggers; no other skill would plausibly collide with it. Not 4 because the overlap risk is essentially zero, not merely minor.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

joelhooks/joelclaw

Path

skills/egghead-slack/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.