Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
camacho avatar

Position

  • 323 installs
  • 1 repo stars
  • Updated May 26, 2026
  • camacho/ai-skills

position is an AI agent skill that bootstraps coding sessions into a persistent team role by loading position profiles from ai-workspace/team/<name>.md for developers who run multi-agent workflows with defined role ident

About

position is an AI agent skill from camacho/ai-skills that bootstraps a coding session into a persistent teammate role instead of a blank context. Invoked as /position <name>, it loads a position profile from ai-workspace/team/<name>.md, optionally loads sibling state directories containing PLAYBOOK and DECISIONS files, and executes the profile-defined session-start bootstrap sequence. Developers reach for position when multi-agent workflows require each session to assume a consistent role identity—such as TPM or other defined positions—before substantive coding begins. The skill generalizes bespoke per-role commands like /tpm into one generic loader pattern, keeping role contracts as reviewable markdown in the ai-workspace tree. Position is not a product-marketing positioning tool despite catalog noise; the readme defines it strictly as teammate session bootstrap for agent pipelines.

  • Frames differentiation versus rivals
  • Sharpens value proposition and narrative
  • Informs audience and pricing follow-ons
  • Grounds GTM copy in competitive reality
  • Pairs with plan and to-prd in ai-skills

Position by the numbers

  • 323 all-time installs (skills.sh)
  • Ranked #234 of 853 Sales & Marketing skills by installs in the Skillselion catalog
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/camacho/ai-skills --skill position

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs323
repo stars1
Last updatedMay 26, 2026
Repositorycamacho/ai-skills

How do you bootstrap an agent into a persistent team role?

Clarify product positioning, differentiation, and target narrative by analyzing competitors and framing why your offering wins a specific audience segment.

Who is it for?

Developers running multi-agent repositories who store role contracts as markdown profiles under ai-workspace/team/ and need sessions to assume those identities on demand.

Skip if: Developers seeking product positioning, competitor analysis, or go-to-market narrative work—the catalog blurb is misleading and the skill only loads agent role profiles.

When should I use this skill?

A teammate coding session must assume a named persistent role identity such as tpm before starting implementation or review work.

What you get

Loaded position profile, initialized PLAYBOOK and DECISIONS state, and an active role-bound agent session ready for work.

  • bootstrapped role session
  • loaded PLAYBOOK and DECISIONS state

Files

SKILL.mdMarkdownGitHub ↗

/position — load a team position into the session

/position <name> is the generic teammate-bootstrap skill. It loads a position profile from ai-workspace/team/<name>.md and runs the bootstrap sequence the profile defines. Replaces the bespoke /tpm (which, where present, is a thin wrapper around /position tpm that adds a unidirectional refusal contract — see "Wrapper skills" below).

Position vs role

  • Position = persistent identity, loaded once per teammate session. Lives in ai-workspace/team/<name>.md. Examples: tpm, software-engineer, technical-editor, architect.
  • Role = one-shot activity dispatched at a /task step. Lives in ai-workspace/agents/<name>.md. Examples: implementer, code-reviewer, test-writer, explorer.

/position operates on positions only. For one-shot role dispatch, use your tool's subagent-dispatch mechanism — Claude Code: Agent({subagent_type: <role-name>}); Codex/Cursor: see your project's AGENTS.md §Agent Roles for the equivalent dispatch pattern.

1. Resolve position

NAME="<arg>"
PROFILE="ai-workspace/team/${NAME}.md"
STATE_DIR="ai-workspace/team/${NAME}"

Pre-flight: if $PROFILE does not exist, refuse with:

Position <name> not found at ai-workspace/team/<name>.md. Available positions: list them by running ls ai-workspace/team/*.md. (For one-shot subagent role dispatch instead, use your tool's role-dispatch mechanism — Claude Code: Agent({subagent_type: <role>}).)

Do not auto-bootstrap. Absence is a signal to verify the environment.

2. Load profile + state

Read in order. Load all files into context first, then reason — do not summarize as you read.

1. $PROFILE (required) — the position's role identity, working agreement, decision rules, triggers, anti-patterns, lifecycle hooks. 2. ${STATE_DIR}/PLAYBOOK.md (if exists) — the position's operating manual. 3. ${STATE_DIR}/DECISIONS.md (if exists) — the position's append-only judgment log.

Most positions have NO sibling state directory — only stateful positions (currently just tpm) do. The skill silently skips state-load when the directory is absent.

3. Regenerate live state (if profile prescribes it)

The position's profile body specifies whether/how to regenerate live state on session start. Common patterns:

  • TPM: gh project item-list + git worktree list + gh pr list
  • Software-engineer: tail #general chat + read .branch-context.md if resuming
  • Technical-editor: tail #general chat for review requests

Follow the profile's ## Session lifecycle / Session start section verbatim. The skill doesn't prescribe regeneration steps — the profile owns them.

4. Acknowledge + take the position

After load + bootstrap:

1. Acknowledge: Position '<name>' loaded. Following profile session-start instructions. 2. Hold the position for the rest of the session — the agent operates as @<name> according to profile rules until session end. 3. Chat handle (if the position's chat substrate is online): post the registration message the profile prescribes.

5. --resume flag (optional)

/position <name> --resume signals resumption of an interrupted session:

  • Read .branch-context.md if present (per the position's profile resume convention)
  • Skip the registration chat post (the position is presumed already known to the team)
  • Pick up where the prior session left off

If the profile has no resume semantics, --resume is a no-op silently.

6. Switching positions

A session can switch positions by re-invoking /position <other>. Latest wins. Profile rules from the prior position drop. Exception: the tpm position has a unidirectional refusal contract (enforced by the /tpm wrapper skill, where installed) — switching out of TPM mid-session is refused per its own rules.

Anti-patterns

Anti-patternWhy wrong
Reading from ai-workspace/agents/ for /positionThat's the role directory (subagents). Positions live in team/.
Auto-bootstrapping a missing positionRefusal is the contract — positions must be defined first
Soft-loading just the profile without the state dirStateful positions need both; skipping state breaks continuity
Summarizing the profile as you load itLoad first, reason second — same as /tpm v0 contract
Treating /position <subagent-role> as valid (e.g. /position implementer)Roles are not positions; refuse and direct to your tool's role-dispatch mechanism (Claude Code: Agent({subagent_type: <role>}))

Invocation forms

  • /position <name> — load position, run bootstrap
  • /position <name> --resume — same, but resume semantics if the profile defines them

Wrapper skills

A position can ship with a sibling wrapper skill that adds position-specific lifecycle behavior on top of /position. Wrappers are optional — /position <name> always works directly. If a wrapper is installed alongside /position in the same skills repo, prefer the wrapper for the position it covers (it handles position-specific contracts the generic loader can't).

Example: /tpm (where shipped as a separate skill) is the wrapper for the tpm position — it invokes /position tpm and adds a unidirectional refusal contract. If /tpm is not installed in your environment, use /position tpm directly; the position loads cleanly without the wrapper, just without the refusal-contract enforcement.

Quick reference

StepActionOn failure
1Resolve team/<name>.mdRefuse with available positions list
2Read profile + state dirSilently skip state if dir absent
3Regenerate live state per profile
4Acknowledge + hold position
5Honor --resume if presentNo-op if profile has no resume semantics
6Switch positions on re-invokeRefuse for unidirectional positions (tpm)

Related skills

How it compares

Pick position over ad-hoc role prompts when role contracts live as versioned markdown and every session must load the same bootstrap sequence.

FAQ

What does the position skill actually load?

position loads a teammate role profile from ai-workspace/team/<name>.md and runs that profile's session-start bootstrap sequence. If a sibling state directory exists, position also loads PLAYBOOK and DECISIONS files so the agent resumes with shared team context.

How do you invoke position in an agent session?

position is invoked with /position <name>, where name matches a markdown profile under ai-workspace/team/. The skill replaces bespoke per-role commands like /tpm with one generic loader that applies whatever bootstrap sequence the profile defines.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.