channel-hygiene
Fix a team's chat sprawl — the channel map with one purpose per channel, the naming scheme that makes purpose findable, the archive pass for the dead and duplicated, and the posting norms (threads, @-discipline, urgency signals) that keep signal findable
Install / Use
npx skills add mohitagw15856/pm-claude-skills --skill channel-hygieneInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
CommunicationSupported Platforms
Our assessment of channel-hygiene
channel-hygiene scores 82/100 on our quality scale, 341st of 421 Communication skills we index.
Its SKILL.md is 5.2 KB long, well organised into 12 sections and no code examples: a solid amount of guidance for an agent.
With 1,396 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated 8 days ago, so channel-hygiene is actively maintained.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
channel-hygiene compared with similar skills
All 4 of these similar skills score higher than channel-hygiene; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| channel-hygiene (this skill)by mohitagw15856 | 82 | 1.4k | 8d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 10d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 10d ago | SKILL.md |
| designby nextlevelbuilder | 100 | 130.2k | 11d ago | SKILL.md |
| ui-ux-pro-maxby nextlevelbuilder | 100 | 130.2k | 11d ago | SKILL.md |
Frequently asked questions
- How do I install channel-hygiene?
- Run
npx skills add mohitagw15856/pm-claude-skills --skill channel-hygiene. The install tabs above show the steps for each supported agent. - Which AI agents does channel-hygiene work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is channel-hygiene safe to use?
- It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is channel-hygiene still maintained?
- The repository was last updated 8 days ago, so channel-hygiene is actively maintained.
Skill content
View source on GitHubname: channel-hygiene description: "Fix a team's chat sprawl — the channel map with one purpose per channel, the naming scheme that makes purpose findable, the archive pass for the dead and duplicated, and the posting norms (threads, @-discipline, urgency signals) that keep signal findable. Use when asked clean up our Slack/Teams, we have 90 channels and nothing is findable, set channel norms, or where should things get posted. Produces the channel audit and map, the naming scheme, the norms card, and the archive pass."
Channel Hygiene Skill
Chat workspaces sprawl by entropy: a channel per whim, three channels where one topic lives, dead projects' channels haunting the sidebar, and every question answered with "wasn't that discussed somewhere?" Hygiene is structural: one purpose per channel (stated in the topic line), a naming scheme that sorts and signals (#proj-, #team-, #help-), an archive pass for the dead (archiving is free and reversible — the fear is misplaced), and posting norms that keep conversations findable — threads for discussions, @-mentions priced honestly, urgency signaled by convention instead of ALL CAPS hope.
What This Skill Produces
- The channel audit — every channel: purpose (stated or guessed), last-activity, overlap verdicts
- The map and naming scheme — the prefix taxonomy, the one-purpose rule, topic lines written
- The norms card — threads, @-discipline, urgency signals, and where-to-post routing — one screen, pinned
- The archive pass — the dead and duplicated archived, with the it's-reversible announcement
Required Inputs
Ask for these if not provided:
- The channel census — the list with member counts and last-activity (export or eyeball); the audit works on inventory, not impressions
- The recurring confusions — where do announcements go? Why are there three design channels? The map answers the actual questions
- The platform's mechanics — archiving behavior, thread culture, the tools available (channel descriptions, pinned posts) — norms use what exists
- The team's @-pain — is @-channel abused? Are DMs swallowing team knowledge? The norms card weights by symptom
Framework: The Hygiene Rules
- One purpose, stated in the topic: every surviving channel's topic line completes "post here for ___" — channels that need "and" in that sentence are two channels; channels where nobody can complete it are archive candidates. The topic line is the routing card at the point of confusion.
- Prefixes are navigation:
#team-(a group's home),#proj-(temporary, archived at ship — the expiry is the point),#help-(questions, threaded),#ann-(announcements, restricted posting, no discussion) — the sidebar becomes a sorted map, and new-channel creation inherits the scheme's discipline. - Archive without fear, loudly: channels dead >90 days get archived with the announcement stating the two facts that kill the objections: archives are searchable and un-archiving takes one click. Duplicated topics merge into the survivor with a pointer post. The sidebar halving is the visible win that funds the norms' adoption.
- Threads keep channels skimmable: discussions thread; the channel surface stays scannable headlines. The norm is stated positively ("thread replies so the channel stays skimmable") and modeled by the leads — thread culture is caught, not decreed.
- @-signals are priced, urgency is explicit: @-channel = "everyone must see this today" (rare by definition) · @-person = "you specifically, action expected" · no-@ = ambient. Urgent-and-blocking gets its stated convention (the 🔴 prefix, the
#help-urgentlane — whatever's chosen, it's written), because unpriced attention signals inflate until everyone mutes everything — and DMs about team topics get the gentle norm: ask in the channel, so the answer compounds (faq-builder feeds on this).
Output Format
Channel Hygiene: [workspace] — [N] channels → [M]
The Audit
| Channel | Purpose (topic-line test) | Last active | Verdict | |---|---|---|---|
The Map + Scheme
[Prefix taxonomy · surviving channels with written topic lines · the new-channel rule]
The Norms Card (pin this)
[Threads · @-pricing · the urgency convention · where-to-post routing · the ask-in-channel-not-DM nudge]
The Archive Pass
[The list · the merge pointers · the announcement with the two fear-killers]
Quality Checks
- [ ] Every surviving channel passes the topic-line test
- [ ] The prefix scheme covers team/project/help/announce with project expiry noted
- [ ] The archive announcement states searchable + reversible
- [ ] The norms card fits one screen and is pinned where confusion happens
- [ ] @-signals and the urgency convention are written, not folklore
Anti-Patterns
- [ ] Do not audit by memory — the census with last-activity dates is the ground truth
- [ ] Do not delete when archiving exists — reversibility is what makes the pass politically free
- [ ] Do not create channels per mood — the naming scheme is the door, and the door has a test
- [ ] Do not let announcements and discussion share a channel — the restricted
#ann-lane exists so the signal survives - [ ] Do not decree thread culture — leads model it for two weeks and it installs itself
Related Skills
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
design
130.2kComprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG…
ui-ux-pro-max
130.2kUI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, and stack-specific UI implementation.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
