Action Runner Skill
The library is great at recommending work. This skill executes it — the action layer of the
Professional Brain (Phase 2). A skill says "open a ticket per
checklist item"; this turns that into real GitHub/Linear/Slack actions, safely: previewed,
risk-rated, approved, then recorded. The cardinal rule: nothing acts silently.
What This Skill Produces
- A dry-run actions plan — every proposed action with its target, operation, and risk.
- After approval, the executed actions (via the connected action MCP) — outbound/destructive
ones gated individually.
- A record back to the brain of what was actually done, with provenance.
Required Inputs
Ask for (if not already provided):
- The recommendations to act on (a launch checklist, PRD requirements, postmortem follow-ups…).
- The connected action MCP and targets — which GitHub repo / Linear project / Slack channel. Scope is limited to what the user names; never act outside it.
- Approval posture — what may run with a single OK vs. what needs per-action confirmation.
How it works
recommend → build an actions plan (JSON) → preview + risk-gate → approve → execute → record
- Build the plan — express each action as JSON:
{"target","op","args","why","risk?"}.
- Preview + gate — run the helper; it prints a dry-run, classifies risk (🟢 low / 🟡 medium /
🔴 high), and refuses to proceed while any 🔴 outbound/destructive action is unapproved:
echo '<plan json>' | python3 scripts/action_preview.py -
# after the user approves the risky ones:
echo '<plan json>' | python3 scripts/action_preview.py - --allow-high
- Approve — low/medium can run on a single confirmation; every 🔴 (post, send, delete, deploy,
merge, charge…) needs explicit per-action approval. Default is do nothing until told.
- Execute — only approved actions, only via the connected action MCP (e.g. Composio/GitHub
create_issue). One target at a time; stop and report on the first failure.
- Record — append what was actually done to the brain so the loop closes:
python3 ../professional-brain/scripts/brain_write.py ./brain decisions "Filed launch tickets" \
--tag external --body "Opened 7 issues in acme/app from the launch checklist" --commit
Supported action targets
Any action MCP can be wired in; these are the common targets, with example operations and the
default risk the gate applies. Reads are 🟢; anything outbound, destructive, or that spends is 🔴.
| Target |
Example operations |
Default risk |
| GitHub |
create_issue, comment, open_pr · (merge_pr, close 🔴) |
🟡 (🔴 for merge/close) |
| Linear / Jira |
create_issue, update_status, comment |
🟡 |
| Slack |
post_message, reply_in_thread (outbound → always confirm) |
🔴 |
| Notion |
append_block, create_page, update_property |
🟡 (🔴 if it overwrites) |
| Email / Gmail |
send_email (outbound) |
🔴 |
| Calendar |
create_event, invite (outbound) |
🟡 (🔴 if it emails invitees) |
Pick the narrowest target and op that does the job, scope to exactly what the user named, and let the
risk gate decide what needs explicit approval. Outbound messages (Slack/email) are 🔴 by default —
the model never posts on someone's behalf without a per-action yes.
Safety rules (non-negotiable)
- Dry-run by default. The plan is shown before anything runs.
- Approval-gated. No execution without a yes; 🔴 actions are confirmed one by one.
- Scope-limited. Only the repos/channels/projects the user named.
- Logged. Every executed action is recorded to the brain with an
[external] tag and a link.
- No silent retries, no bulk outbound. If a step fails, stop and surface it.
The contract for other skills
An action-aware skill adds a short "Proposes Actions" section: after producing its artifact,
it lists the actions it could take (target · op · why), then hands off to action-runner —
which previews, gates, executes, and records. The skill never executes directly.
Output Format
- Proposed actions — a table: # · target · operation · why · risk.
- Gate result — the preview output; the 🔴 actions needing approval called out explicitly.
- Executed (after approval) — what ran, with links/IDs returned by the MCP.
- Recorded to the brain — the line(s) appended, with provenance.
Quality Checks
Anti-Patterns
- Executing anything without showing the dry-run plan first
- Treating an outbound/destructive action (post, email, delete, deploy) as low-risk
- Acting outside the scope the user named, or fanning out to many targets
- "Helpfully" doing more than was approved
- Forgetting to record what was done — the brain must reflect reality
Example Trigger Phrases
- "File tickets from a checklist."
- "Create issues from a PRD."
- "Execute the recommended next steps."
- "Wire a skill's output into GitHub/Linear/Slack."
1---2name: action-runner3description: "Turn a skill's recommendations into real, executed actions — open the tickets, file the issues, post the updates — safely: dry-run preview, risk-classified, approval-gated, then recorded back to the brain. Use when asked to act on a plan, file tickets from a checklist, create issues from a PRD, execute the recommended next steps, or wire a skill's output into GitHub/Linear/Slack. Produces a dry-run actions plan with per-action risk, executes only after approval via the connected action MCP, and logs what was done. Nothing acts silently."4disable-model-invocation: true # skill-optimizer5metadata:6 source: https://skillmd.com/skills/slipcast-dev/action-runner7---89# Action Runner Skill1011The library is great at *recommending* work. This skill executes it — the action layer of the12[Professional Brain](../professional-brain/SKILL.md) (Phase 2). A skill says "open a ticket per13checklist item"; this turns that into real GitHub/Linear/Slack actions, **safely**: previewed,14risk-rated, approved, then recorded. The cardinal rule: **nothing acts silently.**1516## What This Skill Produces17181. A **dry-run actions plan** — every proposed action with its target, operation, and **risk**.192. After approval, the **executed actions** (via the connected action MCP) — outbound/destructive20 ones gated individually.213. A **record back to the brain** of what was actually done, with provenance.2223## Required Inputs2425Ask for (if not already provided):26- **The recommendations to act on** (a launch checklist, PRD requirements, postmortem follow-ups…).27- **The connected action MCP** and **targets** — which GitHub repo / Linear project / Slack channel. Scope is limited to what the user names; never act outside it.28- **Approval posture** — what may run with a single OK vs. what needs per-action confirmation.2930## How it works3132```33recommend → build an actions plan (JSON) → preview + risk-gate → approve → execute → record34```35361. **Build the plan** — express each action as JSON: `{"target","op","args","why","risk?"}`.372. **Preview + gate** — run the helper; it prints a dry-run, classifies risk (🟢 low / 🟡 medium /38 🔴 high), and **refuses to proceed while any 🔴 outbound/destructive action is unapproved**:39 ```bash40 echo '<plan json>' | python3 scripts/action_preview.py -41 # after the user approves the risky ones:42 echo '<plan json>' | python3 scripts/action_preview.py - --allow-high43 ```443. **Approve** — low/medium can run on a single confirmation; every 🔴 (post, send, delete, deploy,45 merge, charge…) needs explicit per-action approval. Default is **do nothing** until told.464. **Execute** — only approved actions, only via the connected action MCP (e.g. Composio/GitHub47 `create_issue`). One target at a time; stop and report on the first failure.485. **Record** — append what was actually done to the brain so the loop closes:49 ```bash50 python3 ../professional-brain/scripts/brain_write.py ./brain decisions "Filed launch tickets" \51 --tag external --body "Opened 7 issues in acme/app from the launch checklist" --commit52 ```5354## Supported action targets5556Any action MCP can be wired in; these are the common targets, with example operations and the57**default risk** the gate applies. Reads are 🟢; anything outbound, destructive, or that spends is 🔴.5859| Target | Example operations | Default risk |60|---|---|---|61| **GitHub** | `create_issue`, `comment`, `open_pr` · (`merge_pr`, `close` 🔴) | 🟡 (🔴 for merge/close) |62| **Linear / Jira** | `create_issue`, `update_status`, `comment` | 🟡 |63| **Slack** | `post_message`, `reply_in_thread` (outbound → always confirm) | 🔴 |64| **Notion** | `append_block`, `create_page`, `update_property` | 🟡 (🔴 if it overwrites) |65| **Email / Gmail** | `send_email` (outbound) | 🔴 |66| **Calendar** | `create_event`, `invite` (outbound) | 🟡 (🔴 if it emails invitees) |6768Pick the narrowest target and op that does the job, scope to exactly what the user named, and let the69risk gate decide what needs explicit approval. Outbound messages (Slack/email) are 🔴 by default —70the model never posts on someone's behalf without a per-action yes.7172## Safety rules (non-negotiable)7374- **Dry-run by default.** The plan is shown before anything runs.75- **Approval-gated.** No execution without a yes; 🔴 actions are confirmed one by one.76- **Scope-limited.** Only the repos/channels/projects the user named.77- **Logged.** Every executed action is recorded to the brain with an `[external]` tag and a link.78- **No silent retries, no bulk outbound.** If a step fails, stop and surface it.7980## The contract for other skills8182An action-aware skill adds a short **"Proposes Actions"** section: after producing its artifact,83it lists the actions it *could* take (target · op · why), then hands off to `action-runner` —84which previews, gates, executes, and records. The skill never executes directly.8586## Output Format87881. **Proposed actions** — a table: # · target · operation · why · risk.892. **Gate result** — the preview output; the 🔴 actions needing approval called out explicitly.903. **Executed** (after approval) — what ran, with links/IDs returned by the MCP.914. **Recorded to the brain** — the line(s) appended, with provenance.9293## Quality Checks9495- [ ] A dry-run plan is shown before anything executes96- [ ] Every action has a risk level; 🔴 actions are individually approved97- [ ] Execution stays within the named scope and uses only the connected MCP98- [ ] Each executed action is recorded back to the brain with an `[external]` tag99- [ ] On failure, it stops and reports rather than retrying blindly100101## Anti-Patterns102103- Executing anything without showing the dry-run plan first104- Treating an outbound/destructive action (post, email, delete, deploy) as low-risk105- Acting outside the scope the user named, or fanning out to many targets106- "Helpfully" doing more than was approved107- Forgetting to record what was done — the brain must reflect reality108109## Example Trigger Phrases110111- "File tickets from a checklist."112- "Create issues from a PRD."113- "Execute the recommended next steps."114- "Wire a skill's output into GitHub/Linear/Slack."