Write or rewrite a skill used in a Tessl factory: a new skill for an automation, a copy of a published factory skill kept in the repository, or a skill that takes over work a script, a runbook or an earlier skill does today. Use when drafting such a skill, rewriting one that has grown into a numbered procedure, or checking one before it merges.
The canonical home for this skill is tessl/factory-setup
A factory skill runs unattended, one round at a time, on whatever the pull request or ticket shows at that moment. Text that reads well to a person can still send that agent the wrong way. Read Context-driven actors first: it is the principle the rest of this guidance applies. Read Factory skill shape and State in factory skills next, and again before step 3: they say what the finished skill looks like. The last, Taking over from what runs today, says how to learn from whatever the skill replaces. Keep working notes in a directory the repository ignores, never in the change itself.
Learn what the skill replaces, when it takes over work another system does (a script, a runbook, a GitHub Actions workflow, an agent harness) or rewrites an existing skill: follow Taking over from what runs today. You end with the outcomes and rules the incumbent holds, each mapped to a platform mechanism, the skill text or a gap, and for a rewrite a classification of every paragraph of the current text. A new skill that replaces nothing starts at step 2.
List the environment facts and check each one against the repository's
default branch, fetched first: what the skill's tools print, what starts a
round and what does not (the automation's triggers or schedule in
tessl.json), which other automations the skill's own writes start (an
issue it labels tessl starts Implement), and what bots and reviewers do.
For each fact, find what makes it true: a file, a trigger, a command's
output. Delete a fact you cannot find, and say instead what the agent cannot
rely on.
Draft to the shape: what done looks like, invariants, environment facts,
judgment. Wire a new skill as Write your own
automation
says. A scheduled one that writes takes a concurrency key with limit: 1,
as turn-findings-into-tickets does in
triggers, so two runs never
overlap. Its SKILL.md frontmatter links its input schema; without the link
the schema is not checked:
schemas:
inputs:
$ref: ./schemas/inputs.schema.jsonWalk concrete cases with a reviewer who has not seen your work: a
subagent, or a fresh session. Give it the skill text and a list of cases,
each a real pull request or ticket state (link real ones where they exist)
with the action you expect. Ask what an agent following only the text would
do in each case and which line it relied on; then ask for contradictions,
facts to check against named files, rules whose absence would do harm, and
wording a model would misread. Tell it the shape is decided. Fix what it
finds and walk the cases again. A finding is not a rule to add: ask first
whether the shape, a fact or the agent's judgment already covers the case,
because a sentence written for one case is the start of a numbered
procedure, and most fixes are a deletion or a corrected fact. Put the cases
and the last walk's outcome in the pull request description. A case walk checks the decision; when the
change affects what the agent writes, also run the action once after the
merge with tessl action trigger <name>, giving --input the subject it
should work on (a throwaway pull request or ticket) and a dry-run input if
it writes to real records, and tell the person what it did.
Do not test the wording. Never write a test that matches the text of a
SKILL.md. A script the skill runs gets its own tests; the case walk tests
the text.
boranfurkan/discordlancer
a41c33b
Canonical home
since Nov 3, 2026
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.