Install
$ agentstack add skill-bearded-illirian-trailmark-go-guide ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/go-guide — Add a Conceptual Guide
Captures a durable concept — architectural decision, workflow rule, domain vocabulary — into the project's knowledge folder so future readers (including the same person in three months) can rediscover it without digging through commits.
Step 0 — Choose invocation mode
Three modes cover three lifecycles:
| Mode | Trigger | Behavior | |---|---|---| | interactive | User types /go-guide | Full flow, asks project + topic + title + text | | from-task | Skill('go-guide', mode='from-task', task_slug=…) | ship-first hook after fast-track close; suggests title/text from task context, user edits | | from-epic | Skill('go-guide', mode='from-epic', epic_slug=…) | Epic closure hook; same as from-task but scoped to whole epic |
Step 1 — Select project
Read aihub/projects.yml. Show numbered menu of projects. Wait for user choice or partial-name match.
Save to session context:
{project_id}= chosen project id (slug){project_path}= project's local path{knowledge_root}={project_path}/project-knowledge/guides/
If {project_path} doesn't have project-knowledge/ folder — create it:
mkdir -p "{project_path}/project-knowledge/guides/"
Step 2 — Select topic
A topic is a stable folder grouping guides by subject (e.g. architecture, workflows, terminology, decisions). Ask the user which topic; offer existing topics first:
ls "{knowledge_root}" 2>/dev/null
Show numbered menu + 0. New topic. If user picks new — ask for slug (lowercase, hyphens). Create the folder:
mkdir -p "{knowledge_root}/{topic_slug}/"
Step 3 — Compose title
For interactive mode — ask user for one-line title.
For from-task / from-epic mode — propose a title derived from task/epic slug + brief. Show proposal, wait for user edit or approval.
Convert to filename slug:
"Why we chose SQLite over Postgres" → "why-sqlite-over-postgres.md"
Step 4 — Compose text
interactive — ask user for content. Accept multiline paste.
from-task / from-epic — propose content derived from the source material:
- Task's
task.mdintent + key decisions fromdecision-*.mdfiles - Report highlights ("What was notable" sections)
- Any
note-*.mdcapturing the essence
Show the proposal for user edit before saving. Never save auto-generated content without user approval.
Step 5 — Write file
FILE="{knowledge_root}/{topic_slug}/{title_slug}.md"
cat > "$FILE" /dev/null || true
If {slug} / {N} unknown → hook writes empty; || true guards failure.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: bearded-illirian
- Source: bearded-illirian/trailmark
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.