AgentKit SEO
Overview
Use this skill as the orchestrator for the whole repository. Its main job is to select the right module skill, avoid loading irrelevant platform rules, and sequence cross-platform work in a sane order.
Routing workflow
- Identify the target surface from the request.
- Load only the matching module skill unless the user explicitly asks for a cross-platform pass.
- If the request spans multiple surfaces, start with
agentkit-seo-agent-context-optimization so the factual source of truth is stable before editing platform outputs.
- If the request is only about the skill system itself, read the references in this skill before changing provider adapters or install instructions.
For broad requests with no clear surface:
- Active applications or job-description tailoring: route to
agentkit-seo-cv-ats.
- Recruiter discovery or profile search: route to
agentkit-seo-linkedin.
- Proof-of-work, repositories, or developer credibility: route to
agentkit-seo-github or agentkit-seo-web-portfolio, based on the supplied asset.
- Audience building, posting strategy, or public conversation loops: route to
agentkit-seo-x-twitter.
- Conflicting, scattered, or cross-platform facts: route to
agentkit-seo-agent-context-optimization first.
Token discipline
- Route to one module by default.
- Load the agent context file before platform references only when facts, consistency, or cross-surface rewriting matter.
- Prefer public URL inspection, local search, or a compact pasted section over asking the user to dump every asset into the prompt.
- Summarize inspected inputs and ask for the smallest missing input set.
- Do not expand into algorithm explanation unless the user asks why.
Intake workflow
- If the user already has an agent context file, ask for or use its explicit path before rewriting platform assets.
- If the task spans multiple surfaces, or the user's facts are scattered, recommend creating or repairing the agent context file first.
- Do not block a narrow one-off edit on a full context file when the supplied material is already enough.
- For public URLs, fetch or inspect public material when tools allow it and cite which source was used.
- For private or login-gated surfaces, ask the user for pasted section text, screenshots, exports, or a local text file instead of guessing.
- If critical facts are missing, ask only for the minimum extra inputs needed to proceed.
Module map
- LinkedIn work:
agentkit-seo-linkedin
- GitHub work:
agentkit-seo-github
- CV or ATS work:
agentkit-seo-cv-ats
- Web portfolio work:
agentkit-seo-web-portfolio
- X or Twitter work:
agentkit-seo-x-twitter
- Personal source-of-truth context work:
agentkit-seo-agent-context-optimization
Boundaries
- Do not load every module by default.
- Do not invent platform behavior that the hub has explicitly marked as uncertain or disputed.
- Do not rewrite the shared methodology in provider adapter folders. Keep the portable source of truth in
.skills/agent-skill/.
- When advice depends on current platform capabilities, paid tiers, ranking behavior, product limits, or provider support, verify with current official sources when tools allow it or label the claim as historical, disputed, or inferred.
- For cross-platform outputs, label major claims as
Verified, From context, From supplied source, Official/current source, Inference, Needs evidence, or Inaccessible when the source status could affect the recommendation.
Response shape
For broad requests, return:
- the selected workflow or module
- inputs used and missing inputs
- concrete edits or recommendations
- unresolved risks or assumptions
- next action, preferably creating or updating the context file when that would reduce drift
References
- Read references/module-routing.md when the user request is broad or ambiguous.
- Read references/provider-matrix.md when changing adapter behavior.
- Read references/installation-strategy.md when changing packaging or install guidance.
1---2name: agentkit-seo3description: Route broad or ambiguous AgentKit SEO work to the right module while keeping context scoped. Use when a request spans multiple surfaces, asks for overall digital-presence strategy, involves provider or install architecture, needs agent-context planning, or the correct platform skill is unclear.4---5
6# AgentKit SEO
7
8## Overview
9
10Use this skill as the orchestrator for the whole repository. Its main job is to select the right module skill, avoid loading irrelevant platform rules, and sequence cross-platform work in a sane order.
11
12## Routing workflow
13
141. Identify the target surface from the request.
152. Load only the matching module skill unless the user explicitly asks for a cross-platform pass.
163. If the request spans multiple surfaces, start with `agentkit-seo-agent-context-optimization` so the factual source of truth is stable before editing platform outputs.
174. If the request is only about the skill system itself, read the references in this skill before changing provider adapters or install instructions.
18
19For broad requests with no clear surface:
20
21- Active applications or job-description tailoring: route to `agentkit-seo-cv-ats`.
22- Recruiter discovery or profile search: route to `agentkit-seo-linkedin`.
23- Proof-of-work, repositories, or developer credibility: route to `agentkit-seo-github` or `agentkit-seo-web-portfolio`, based on the supplied asset.
24- Audience building, posting strategy, or public conversation loops: route to `agentkit-seo-x-twitter`.
25- Conflicting, scattered, or cross-platform facts: route to `agentkit-seo-agent-context-optimization` first.
26
27## Token discipline
28
29- Route to one module by default.
30- Load the agent context file before platform references only when facts, consistency, or cross-surface rewriting matter.
31- Prefer public URL inspection, local search, or a compact pasted section over asking the user to dump every asset into the prompt.
32- Summarize inspected inputs and ask for the smallest missing input set.
33- Do not expand into algorithm explanation unless the user asks why.
34
35## Intake workflow
36
37- If the user already has an agent context file, ask for or use its explicit path before rewriting platform assets.
38- If the task spans multiple surfaces, or the user's facts are scattered, recommend creating or repairing the agent context file first.
39- Do not block a narrow one-off edit on a full context file when the supplied material is already enough.
40- For public URLs, fetch or inspect public material when tools allow it and cite which source was used.
41- For private or login-gated surfaces, ask the user for pasted section text, screenshots, exports, or a local text file instead of guessing.
42- If critical facts are missing, ask only for the minimum extra inputs needed to proceed.
43
44## Module map
45
46- LinkedIn work: `agentkit-seo-linkedin`
47- GitHub work: `agentkit-seo-github`
48- CV or ATS work: `agentkit-seo-cv-ats`
49- Web portfolio work: `agentkit-seo-web-portfolio`
50- X or Twitter work: `agentkit-seo-x-twitter`
51- Personal source-of-truth context work: `agentkit-seo-agent-context-optimization`
52
53## Boundaries
54
55- Do not load every module by default.
56- Do not invent platform behavior that the hub has explicitly marked as uncertain or disputed.
57- Do not rewrite the shared methodology in provider adapter folders. Keep the portable source of truth in `.skills/agent-skill/`.
58- When advice depends on current platform capabilities, paid tiers, ranking behavior, product limits, or provider support, verify with current official sources when tools allow it or label the claim as historical, disputed, or inferred.
59- For cross-platform outputs, label major claims as `Verified`, `From context`, `From supplied source`, `Official/current source`, `Inference`, `Needs evidence`, or `Inaccessible` when the source status could affect the recommendation.
60
61## Response shape
62
63For broad requests, return:
64
651. the selected workflow or module
662. inputs used and missing inputs
673. concrete edits or recommendations
684. unresolved risks or assumptions
695. next action, preferably creating or updating the context file when that would reduce drift
70
71## References
72
73- Read [references/module-routing.md](references/module-routing.md) when the user request is broad or ambiguous.
74- Read [references/provider-matrix.md](references/provider-matrix.md) when changing adapter behavior.
75- Read [references/installation-strategy.md](references/installation-strategy.md) when changing packaging or install guidance.
majiayu000