Langsmith Observability
Orchestra-Research/AI-Research-SKILLs
LLM observability platform for tracing, evaluation, and monitoring.
Observe answer visibility for approved buyer questions, audit discoverability and file evidence-backed improvement cards.
$ npx skills add markfulton/ai-employees --skill seo-answer-visibility -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install markfulton/ai-employees seo-answer-visibility --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/markfulton/ai-employees.git skills-src && mkdir -p .claude/skills && cp -r skills-src/employees/seo-employee/routines/seo-answer-visibility .claude/skills/seo-answer-visibility && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "seo-answer-visibility" agent skill from https://github.com/markfulton/ai-employees/tree/main/employees/seo-employee/routines/seo-answer-visibility into .claude/skills/seo-answer-visibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-answer-visibility", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/markfulton/ai-employees/tree/main/employees/seo-employee/routines/seo-answer-visibilityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add markfulton/ai-employees --skill seo-answer-visibility -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install markfulton/ai-employees seo-answer-visibility --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/markfulton/ai-employees.git skills-src && mkdir -p .agents/skills && cp -r skills-src/employees/seo-employee/routines/seo-answer-visibility .agents/skills/seo-answer-visibility && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "seo-answer-visibility" agent skill from https://github.com/markfulton/ai-employees/tree/main/employees/seo-employee/routines/seo-answer-visibility into .agents/skills/seo-answer-visibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-answer-visibility", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add markfulton/ai-employees --skill seo-answer-visibility -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install markfulton/ai-employees seo-answer-visibility --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/markfulton/ai-employees.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/employees/seo-employee/routines/seo-answer-visibility .cursor/skills/seo-answer-visibility && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "seo-answer-visibility" agent skill from https://github.com/markfulton/ai-employees/tree/main/employees/seo-employee/routines/seo-answer-visibility into .cursor/skills/seo-answer-visibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-answer-visibility", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/markfulton/ai-employees.git --path employees/seo-employee/routines/seo-answer-visibility--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add markfulton/ai-employees --skill seo-answer-visibility -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install markfulton/ai-employees seo-answer-visibility --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/markfulton/ai-employees.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/employees/seo-employee/routines/seo-answer-visibility .gemini/skills/seo-answer-visibility && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "seo-answer-visibility" agent skill from https://github.com/markfulton/ai-employees/tree/main/employees/seo-employee/routines/seo-answer-visibility into .gemini/skills/seo-answer-visibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-answer-visibility", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install markfulton/ai-employees seo-answer-visibilityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add markfulton/ai-employees --skill seo-answer-visibility -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/markfulton/ai-employees.git skills-src && mkdir -p .github/skills && cp -r skills-src/employees/seo-employee/routines/seo-answer-visibility .github/skills/seo-answer-visibility && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "seo-answer-visibility" agent skill from https://github.com/markfulton/ai-employees/tree/main/employees/seo-employee/routines/seo-answer-visibility into .github/skills/seo-answer-visibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-answer-visibility", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add markfulton/ai-employees --skill seo-answer-visibility -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install markfulton/ai-employees seo-answer-visibility --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/markfulton/ai-employees.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/employees/seo-employee/routines/seo-answer-visibility .opencode/skills/seo-answer-visibility && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "seo-answer-visibility" agent skill from https://github.com/markfulton/ai-employees/tree/main/employees/seo-employee/routines/seo-answer-visibility into .opencode/skills/seo-answer-visibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seo-answer-visibility", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
seo-answer-visibilityObserve answer visibility for approved buyer questions, audit discoverability and file evidence-backed improvement cards.
SEO Answer Visibility is an agent skill from markfulton/ai-employees. Observe answer visibility for approved buyer questions, audit discoverability and file evidence-backed improvement cards.
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Open source AI Employees. 8 scheduled business roles, 60 routines, on Claude Code and 10 other harnesses. They drive your browser the way you do and improve every run. You own… The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 37bfe17. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
nodeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
SEO Answer Visibility loads about 2.1k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 1,160 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from markfulton/ai-employees at commit 37bfe17, republished under its MIT licence (© markfulton). 1,160 words, ~2,078 tokens.
.claude/skills/seo-answer-visibility/SKILL.md (or your agent's skills folder).After the guard returns run, read WORK-CYCLE.md and your entry in work-profile.json. Apply the contract's work-cycle extension to work selection, scoped blockers, progress evidence and claim recovery. Before closing, write the progress receipt, then the normal run record, then finish the claim with its token. Preserve the remaining budget on a resume. A same-period run with a claim overrides only the legacy Step 0.2 exit/reset. All pause, release and browser guards still apply.
Run node scripts/guard.mjs seo-answer-visibility --json first. A non-run verdict has already been recorded; exit without reading the rest of the kit. For a run verdict read CONTRACT.md, ROLE.md, CAPABILITIES.md, AEO-PLAYBOOK.md and your SCHEDULE.md row in full. This routine inherits every contract guard, status, state schema, mutex rule and output writer boundary. Never infer a time, budget or cadence from this document.
Read your row and compute its period key using the contract rules and local clock. Read state/seo-answer-visibility.json. Apply the contract's once-per-period check and atomic state update, recording last_period, started, the run id and progress before external work. A real guard run returns an atomic claim. Preserve its token and apply WORK-CYCLE.md recovery rules; an inspection with --no-record reserves nothing. Use the established mutex/stale-lock rules before browser work, and release only the lock you own on every exit. Do not modify another routine's state, schedule or active lock.
Resolve capabilities live. Prefer a confirmed connected read route, then an approved browser session, then a dated member-supplied observation. CAPABILITIES.md is the only vendor-to-capability map. No connector purchase, install, account creation, authentication or credential entry. An unavailable route is an explicit gap, not zero visibility. Read-only observation includes submitting the approved public buyer question to an existing authorized search/chat surface; never include private client notes, secrets or unpublished strategy in that question. Do not use a route whose use requires accepting terms or an unapproved paid action.
Read strategy/properties.md, strategy/answer-map.md, strategy/topic-map.md, the published ledger, the previous answer report, current observations and board/board.json. If properties are missing, record failed with intake as the blocker. If the answer map is missing, file one deduplicated research card for intake; continue an owned-page eligibility review, but never invent the client's target audience or question set.
Pick the highest-priority owned target pages from the answer map within the remaining budget. Read their HTTP status, canonical, visible answer text, internal entry links and available robots/directive evidence. Record the exact URL, date, method and finding. Compare organization and service facts to the approved evidence in the map. A missing capability is unknown, not a failed SEO check. Stage one specific correction per observed problem; never alter robots, CDN, schema, a public profile or a live page from this routine.
Work the fixed question set in stable id order, resuming coverage without exceeding the row budget. Follow the AEO-PLAYBOOK observation contract exactly. Distinguish each consumer surface from any API route. Capture the answer and its cited links, not just a search snippet about an answer. If a mode does not use retrieval, label it and keep it out of grounded-search comparisons.
Write each observation as a validated UTF-8 JSONL line once, with a stable id of run id + question id + surface. On retries, check that id before appending. Save only the evidence needed to verify the claim, strip secrets and unrelated account information, and reference its local path. Never overwrite earlier observations. Login walls stop work on that surface immediately; record blocked-login using the contract and continue file work if possible. No captcha retries, session sharing or attempts to evade platform limits.
Review what cited pages actually answer, using permitted fetches. Do not copy competitor prose. Identify which important buyer question is unanswered, which assertion lacks proof, which business fact conflicts, or which owned page is technically unavailable. A competitor mention alone does not demonstrate a defect in the client's page.
Apply the playbook's action order. Append prioritized, deduplicated cards using CONTRACT.md's exact inbox schema and existing types; read that schema before writing. Use refresh for an existing page improvement, new-post only for a missing canonical answer, research for missing evidence, and technical or verify for an owner action. Set done_kind to member-action for owner actions and local-artifact for a kit-owned draft/publish deliverable. Set owner to seo-draft-run only for executable content work; do not route infrastructure or outreach into the drafting runner. Include the source question id, evidence path/date, target URL, expected deliverable, responsible party and acceptance check in the card's allowed text fields. Do not invent new JSON fields or card types. Only standup assigns card ids and changes board order. Persist normalized proposed_keys in this routine's state and check them before each append; only standup reads the inbox.
Acceptance examples: approved service facts agree on the cited pages; a buyer question has a direct sourced answer on the canonical page; a permitted case study includes its method and date; a target page passes the owner's indexability check. Never use "ChatGPT must recommend us" or an unsupported traffic target as acceptance.
Write a dated report under tracking/answers/ and atomically replace tracking/answer-latest.md only after that report is complete. Include:
At budget, stop at the current question boundary, persist coverage and write a partial report. Do not resubmit a completed question to use up time. On failure retain the previous successful rolling report with its original date; write the new failure to your state and run record. If file work succeeded but external observation was unavailable, report partial and coverage unknown, with the precise blockers. Apply the closed statuses from CONTRACT.md rather than inventing an AEO status.
Finish with the standard run record through scripts/runlog.mjs and its documented input contract. Include output paths, card ids, progress, blockers and assumptions. Release your browser lock and close only your own tabs in a finally-style cleanup. A log failure uses the contract's UNRECORDED RUN fallback; never silently report success. This routine never publishes, contacts prospects, changes infrastructure, spends, or writes RELEASES.md.
Read GSC-GENERATIVE-AI.md for report definitions, ownership and validation. Before question sampling, collect native Generative AI impressions using the current property map. Append validated observations and write the dated native report. This work does not require an answer-question map or previously published kit content. If that map is absent, still read the mapped property report and continue factual eligibility checks.
No corrections recorded yet. Preserve member corrections when upgrading.
© markfulton, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in employees/seo-employee/routines/seo-answer-visibility of markfulton/ai-employees.
Open the folder on GitHubat commit 37bfe17
SEO Answer Visibility next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| SEO Answer Visibility this skillmarkfulton/ai-employees | 495 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Langsmith ObservabilityOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~2.4k | Automated safety check: Pass | MIT | |
| ObservabilityBuilderIO/agent-native | 7.1k | — | ~7k | Automated safety check: Pass | None | |
| Observability And Instrumentationsickn33/agentic-awesome-skills | 47k | 1 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Agent Observabilitysickn33/agentic-awesome-skills | 47k | 2 repos | ~3k | Automated safety check: Pass | MIT | |
| Frontend Observabilitysickn33/agentic-awesome-skills | 47k | 1 repos | ~5.1k | Automated safety check: Pass | MIT |
Orchestra-Research/AI-Research-SKILLs
LLM observability platform for tracing, evaluation, and monitoring.
BuilderIO/agent-native
Agent observability, evals, feedback, and experiments. An agent skill from BuilderIO/agent-native.
sickn33/agentic-awesome-skills
Instruments code so production behavior is visible and diagnosable.
sickn33/agentic-awesome-skills
Instrument AI agents with tracing, token metrics, latency, and cost visibility.
sickn33/agentic-awesome-skills
A portable, framework-agnostic field-side observability system for any React or React Native app.
sickn33/agentic-awesome-skills
Use eBPF for deep kernel-level observability — trace syscalls, network flows, and application behavior without code changes using Cilium, Tetragon, and bpftrace.
markfulton/ai-employees
Hire one of the eight open source AI Employees (GTM Engineer, SEO/AEO, Web Dev, Social Media, Ad Manager, Sales, Customer Satisfaction, Chief of Staff) into a local folder, prove it runs, and hand…
markfulton/ai-employees
Runs once by hand on the first day and once a month after that.
markfulton/ai-employees
Weekdays. An agent skill from markfulton/ai-employees.
markfulton/ai-employees
Weekdays. An agent skill from markfulton/ai-employees.
markfulton/ai-employees
Weekly, on a Friday, read only everywhere. An agent skill from markfulton/ai-employees.
markfulton/ai-employees
Monthly, on the last weekday. An agent skill from markfulton/ai-employees.
Observe answer visibility for approved buyer questions, audit discoverability and file evidence-backed improvement cards. SEO Answer Visibility is an agent skill from markfulton/ai-employees. Observe answer visibility for approved buyer questions, audit discoverability and file evidence-backed improvement cards.
Run `npx skills add markfulton/ai-employees --skill seo-answer-visibility -a claude-code`. Or copy the skill folder (employees/seo-employee/routines/seo-answer-visibility in markfulton/ai-employees) into .claude/skills/seo-answer-visibility in your project. Claude Code loads it when a task matches its description.
Run `npx skills add markfulton/ai-employees --skill seo-answer-visibility -a codex`. Or copy the skill folder (employees/seo-employee/routines/seo-answer-visibility in markfulton/ai-employees) into .agents/skills/seo-answer-visibility in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add markfulton/ai-employees --skill seo-answer-visibility -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seo-answer-visibility, .gemini/skills/seo-answer-visibility, .github/skills/seo-answer-visibility and .opencode/skills/seo-answer-visibility in your project.
Going by SKILL.md and its folder, SEO Answer Visibility needs the command-line tools its instructions call (node).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
SEO Answer Visibility is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with SEO Answer Visibility: Langsmith Observability (Orchestra-Research/AI-Research-SKILLs, 13k stars), Observability (BuilderIO/agent-native, 7.1k stars), Observability And Instrumentation (sickn33/agentic-awesome-skills, 47k stars) and Agent Observability (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
markfulton (a GitHub user) maintains it in markfulton/ai-employees, which has 495 GitHub stars. The repository holds 60 skills in this directory. The repository was last updated on October 7, 2026.
Source: markfulton/ai-employees on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.