Developing Tessl Skills
Runs the complete local development lifecycle for a Tessl skill by optimizing SKILL.md content using `tessl skill review --optimize`, incrementing the version in tile.json following semantic versioning, linting with `tessl skill lint`, and staging changes for a pull request. Use when preparing a Tessl skill for pull request or publication, when a SKILL.md or tile.json needs to be reviewed, versio…
Install
$ agentstack add skill-nagaakihoshi-skills-developing-tessl-skills Open-source listing, not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Pipes remote content directly into a shell (remote code execution).
What it can access
- ● Network access Used
- ✓ 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.
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
Overview
This skill covers the complete local development lifecycle for a Tessl skill before opening a pull request. It ensures the skill is optimized, properly versioned, and validated.
Prerequisites
- Tessl CLI installed:
curl -fsSL https://get.tessl.io | sh - Logged in:
tessl login
Steps
1. Identify the skill path
Confirm the skill directory (e.g., skills//) contains both tile.json and SKILL.md.
2. Optimize the skill
tessl skill review --optimize skills/- Iterates up to 3 times, applying best-practice improvements automatically.
- Accept the proposed changes when prompted, or use
--yesto auto-accept. - Aim for a score of 70% or higher. If the score is still below threshold, re-run with
--max-iterations 10.
3. Increment the version in tile.json
Open skills//tile.json and increment version following semantic versioning:
| Change type | Example | |---|---| | Bug fix or minor wording improvement | 0.1.0 → 0.1.1 | | New capability, backward-compatible | 0.1.0 → 0.2.0 | | Breaking change to skill behavior | 0.1.0 → 1.0.0 |
4. Validate
tessl skill lint skills/Confirm the output shows the tile as valid before committing.
If lint fails: review the reported errors, fix the issues in SKILL.md or tile.json, then re-run tessl skill lint until it passes before proceeding.
5. Commit and open a PR
Stage all changes to SKILL.md and tile.json, commit, and open a pull request against main. CI will run tessl skill lint automatically on the PR.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: nagaakihoshi
- Source: nagaakihoshi/skills
- 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.