social-text
Write forge-facing text (issues, pull-request bodies, review comments, commit bodies, changelog titles): scannable human prose derived from adhd-format; keeps…
Skill by plurano
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/plurano-social-text
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/social-text
What's inside
- Skill name
social-text- Description
- Write forge-facing text (issues, pull-request bodies, review comments, commit bodies, changelog titles): scannable human prose derived from adhd-format; keeps PR template, receipt fence, conventional commits, Keep-a-Changelog intact.
- License
- EUPL-1.2
- Metadata
- derived_from: https://github.com/ayghri/i-have-adhd (MIT)
- Instructions
- 83 lines in SKILL.md · view on GitHub
Files (2)
- LICENSE
- SKILL.md
SKILL.md (first lines)
# Social register for the forge (`social-text`) Adapted from [i-have-adhd](https://github.com/ayghri/i-have-adhd) by Ayoub Ghriss and [contributors](https://github.com/ayghri/i-have-adhd/graphs/contributors) via adhd-format; MIT licence. Use this skill for forge text a person reads: issue, pull-request body, review comment, commit body, changelog fragment title. = `social` register of text-register policy (`register:` in `.standards.yaml`; "Text Register" section of AGENTS.md). Agent-to-agent text -> `internal` register, documentation -> `docs` register; neither uses this skill. ## Inherited from adhd-format Skill inherits 3 `adhd-format` principles; item 2 adds the line-break and list rules: 1. **Bottom line first**: first sentence = decision, defect or ask. 2. **Scannable structure**: - paragraphs of one to three sentences, one idea each; - bold operative words of action bullet; - a list whenever three or more parallel items appear, never a comma chain; - a blank line before and after every list, table and heading; - a table when three or more items are compared across two dimensions. 3. **Progressive disclosure**: summary first, commands second, detail linked or collapsed below. Overrides rest of adhd-format for humans: at most 1 GitHub alert per text; no Mermaid unless flow is point of change; tables only for 3+ rows; no emoji headings; no anchor bolding in running prose. ## Voice - Full sentences, plain words. Maintainer must act on text without opening diff. - One idea per paragraph or bullet. Name file and line (`.agents/skills/caveman/SKILL.md:42`) when reader will look there. - Say 4 things, then stop: what changed, why, how verified, what reviewer must decide. Pull-request summary stays around 250 words before evidence links. - No meta-commentary (`as requested`, `based on my analysis`), no hedging filler, no code restatement diff already shows. - Quote operator paraphrased in neutral English; never verbatim colloquial line. - No tool attribution anywhere: no `Co-Authored-By` naming model or tool, no `generated with` footer (AGENTS.md rule 12). Strip such footer when editing existing body. ## Evidence Link or attach evidence; never paste beyond inline bound (`register.evidence`, default 58 lines / 1500 tokens). Test log, SARIF file or transcript -> `evidence: <path> sha256:<12 hex> lines:<n>`, or attached file. Signed receipt = one exception, pasted where template asks for it. ## Standards this register does not change **Pull-request body.** Fill the pull request template exactly as shipped. Social register governs only prose under `## Summary of Changes`. Sections 1-4 (HISS-16 checklist, 3D-testing verification, context-integrity checklist, receipt) = filled, never rewritten, reordered or removed. Receipt goes inside fence labelled `receipt`; unlabelled fence not read by validator. **Commit message.** Subject stays conventional commit, `type(scope): subject`, `type` one of `feat | fix | docs | style | refactor | perf | test | build | ci | chore | revert`. Commit-msg hook rejects other shape, requires `Signed-off-by` trailer. Keep subject near 72 characters; hook does not measure it, reader's terminal does. Breaking change carries `!` in subject, `Migration:` footer (HISS-14). Only body written in this register: why first, then what, wrapped at 72 columns. **Changelog.** Never edit `CHANGELOG.md` directly. Write one fragment `<date>-<slug>.yaml` in the changelog fragment directory with `type` from `added | changed | deprecated | removed | fixed | security`, one-sentence imperative `title`, optional `issue`, `breaking: true` when applicable. Register shapes title only. **Issue.** Title = defect in one sentence. Body: observed, expected, reproduction commands, evidence pointers. Search open issues, pull requests before filing (AGENTS.md rule 5). **Review comment.** One finding per comment; severity word first, then file:line, then fix. Address code, not author.
From plurano/peritia, EUPL-1.2.
More from plurano/peritia
- 0.565score
caveman
plurano
Caveman form for internal agent traffic (briefs, agent returns, research fan-outs, workflow returns, tool-call notes).
SkillAFreshness: AClaude Code +9 - 0.565score
agent-security-hardening
plurano
Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle…
SkillAFreshness: AClaude Code +9 - 0.561score
adhd-format
plurano
Format complex technical reports, architectural reviews, and diagnostic outputs for high cognitive focus, executive clarity, and ADHD readability using visual…
SkillAFreshness: AClaude Code +9 - 0.561score
agent-runtime-gateway-smoke-test
plurano
Verify a local agent API, temporary gateway tunnel, and remote sandbox callback with a tool-free task, then restore the original app connection.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Oct 15, 2026 (13 days ago)
- Last release
- Oct 15, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- EUPL-1.2
- Repository
- github.com/plurano/peritia
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from plurano
- 0.565score
caveman
plurano
Caveman form for internal agent traffic (briefs, agent returns, research fan-outs, workflow returns, tool-call notes).
SkillAFreshness: AClaude Code +9 - 0.565score
agent-security-hardening
plurano
Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle…
SkillAFreshness: AClaude Code +9 - 0.561score
adhd-format
plurano
Format complex technical reports, architectural reviews, and diagnostic outputs for high cognitive focus, executive clarity, and ADHD readability using visual…
SkillAFreshness: AClaude Code +9 - 0.561score
agent-runtime-gateway-smoke-test
plurano
Verify a local agent API, temporary gateway tunnel, and remote sandbox callback with a tool-free task, then restore the original app connection.
SkillAFreshness: AClaude Code +9
Cite this page
social-text skill. Agent Mart. https://agentmart.dev/skills/plurano-social-text (last updated 2026-10-24)