observe · plugin87 — Claude Code skill: what it does, how to install
observe — a skill for Claude Code that checks local hook events to see if the agent followed UX/UI kit rules in recent sessions. Runs manually on user request.
MIT ★ 3,216 updated 2026-11-10
/plugin marketplace add plugin87/ux-ui-agent-skills
/plugin install ux-ui-agent-skills@ux-ui-agent-skillsWhat observe does
This skill inspects session records to check three specific rules. Every edited page must pass a gate before completion, no fast-gate findings can remain on the latest file version, and the agent must not exit while the Stop hook holds open pages. It does not evaluate design quality.
Under the hood it executes scripts/observe.mjs using Node.js. The skill cannot run in isolation: it requires the complete ux-ui-agent-skills kit installed via npx [email protected] init or as a Claude Code plugin. If only the skill directory is added, execution halts with a KIT_MISSING error.
What it helps with
- verify passing gates for every edited UI page
- identify unresolved fast-gate findings in current file versions
- detect sessions finished while the Stop hook had pages open
- export compliance audit results to HTML
Example prompts for the agent
- Run observe for this project over the last 3 days
- Inspect a failed session using observe --session <id>
- Generate an HTML audit summary using observe --html report.html
How to install observe
1Plugin marketplace
/plugin marketplace add plugin87/ux-ui-agent-skills/plugin install ux-ui-agent-skills@ux-ui-agent-skillsThis installs the whole ux-ui-agent-skills plugin with all its skills
2Skills CLI (Vercel)
npx skills add plugin87/ux-ui-agent-skills --skill observe -a claude-code3Manually: put the files in place
~/.claude/skills/observe/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/observe/
1Skills CLI (Vercel)
npx skills add plugin87/ux-ui-agent-skills --skill observe -a codex2Manually: put the files in place
.agents/skills/observe/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add plugin87/ux-ui-agent-skills --skill observe -a cursor2Manually: put the files in place
.cursor/skills/observe/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install plugin87/ux-ui-agent-skills .claude/skills/observe2Manually: put the files in place
.github/skills/observe/SKILL.md1Skills CLI (Vercel)
npx skills add plugin87/ux-ui-agent-skills --skill observe -a gemini-cli2Platform CLI
gemini skills install https://github.com/plugin87/ux-ui-agent-skills --path .claude/skills/observeManually: put the files in place
.devin/skills/observe/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about observe
How to install observe in Claude Code?
Run /plugin marketplace add plugin87/ux-ui-agent-skills and then /plugin install ux-ui-agent-skills@ux-ui-agent-skills. To ensure the scripts exist, initialize the kit with npx [email protected] init.
What does observe do?
It audits recorded hook events to verify whether agent sessions followed the kit's UI rules. The model cannot trigger this skill automatically because disable-model-invocation is set to true.
What is required to run observe?
It requires Node.js and the complete ux-ui-agent-skills setup. Without the local scripts/observe.mjs script and recorded hook events, the skill stops immediately.
Source text
SKILL.md · MIT
--- name: observe description: 'Show whether the agent followed the kit''s rules in recent sessions: pages edited and measured, Stop hook blocks, findings left open. Reads local hook events only.' # A command the user runs, like /gate. The model never starts it. disable-model-invocation: true --- ## Requirements This skill needs the full UX/UI Agent Skills kit: the gates, the references and the design-system library. Install it with `npx [email protected] init` or as the Claude Code plugin. `npx [email protected] add` copies the skill folder and nothing else, and this skill has no guidance-only mode: its whole job is to read what the kit's hooks recorded, so without the kit there is nothing for it to do. > **Step 0: is the kit here?** Check once: > `ls ${CLAUDE_SKILL_DIR}/../../../scripts/observe.mjs >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSING` > On `KIT_MISSING`, say plainly that only the skill folder was installed, name > the install command above, and stop. Do not guess the contents of a file you > could not open, and do not report a result you did not produce. Report what the hooks recorded - never a reconstruction from memory. 1. Run `node ${CLAUDE_SKILL_DIR}/../../../scripts/observe.mjs --project "$CLAUDE_PROJECT_DIR"` (or without `--project` when the user asks about every project, and with `--days N` when they name a window). 2. Quote the summary lines it prints. If it says no session edited UI, say that and stop: there is nothing to judge. 3. For each session marked `BROKE A RULE`, run it again with `--session <id>` and say which rule failed and the timeline line that shows it. 4. If the user wants the page, run it with `--html <path>` and give the path. What it measures, and what it does not: three counted rules per session - every edited page had a passing gate before the end, no fast-gate finding was left on a file's latest version, and the agent never finished while the Stop hook still had pages open. It says nothing about design quality, and an `unfinished` session is not counted for or against.
© Thientan Soparat · MIT · plugin87/ux-ui-agent-skills
Similar skills
All skills for Agent setup: memory, context, orchestration →observe by other authors comes first.