updated 2026-10-17 20:06 UTC

SkillOpt

Repository Website by microsoft

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Agent Skills Python Listed MIT

Is SkillOpt safe? Promising trust profile, but some evidence still deserves review.

OSSF Scorecard 6.1 / 10
Provenance None
Signed commits 56%
Last push today
Advisories None known
Compare SkillOpt

How does it stack up against its Agent Skills neighbours?

Pick any agent to compare →
Suggest a correction

In detail: SkillOpt scores 70.5/100 (Grade B), ranked #30 of 385 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 6.1/10; 56% of recent commits are signed; no published advisory affects its latest release (skillopt); last pushed 2026-10-17. Every point is earned from checkable signals — never paid placement. How scoring works →

How SkillOpt could raise its score

Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.

Already done? Suggest a correctionAdd the trust badge

Chain of custody

Scanners check what the code says. This traces who ships SkillOpt and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities and, for skills, AST02 Supply Chain Compromise.

  1. Source Partly signed

    github.com/microsoft/SkillOpt, MIT, last pushed 2026-10-17. 56% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.

  2. Review and release Mixed

    OpenSSF Scorecard rates the repository's practices 6.1/10 (scanned Sep 28, 2026, refresh pending). The checks that decide who can get a change released:

    • Code Review8
    • Branch Protection0
    • Signed Releasesn/a
    • Dangerous Workflow10
    • Token Permissions0
    • Pinned Dependencies0
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 0
    CI-Tests 0
    CII-Best-Practices 0
    Code-Review 8
    Contributors 10
    Dangerous-Workflow 10
    Dependency-Update-Tool 10
    Fuzzing 0
    License 10
    Maintained 10
    Packaging -1
    Pinned-Dependencies 0
    SAST 0
    Security-Policy 10
    Signed-Releases -1
    Token-Permissions 0
    Vulnerabilities 10

  3. Published packages Linked, not attested

    • PyPI skillopt Source link points back to this repo No build attestation

    Without a build attestation, nothing proves the published files were built from this repository.

  4. What you install today No known advisories

    Latest release checked: skillopt 0.2.0. No published advisory affects it (OSV, checked 2026-10-17).

Changes to this chain

  • 2026-08-30 OSSF Scorecard: 6.0/10

Evidence behind this score

Coverage B: 3 of 5 independent evidence types found.

  • GitHub repository data
  • Package downloads
  • Supply-chain checks
  • Public actions (missing)
  • Community mentions (missing)

Verify this score yourself

Every build re-issues SkillOpt’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read the skill’s instructions for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you install it, such as Cisco Skill Scanner.

How SkillOpt compares in Agent Skills

  1. #28 Arcgentic 71.3 +0.8
  2. #29 Dev Browser 71.2 +0.7
  3. #30 SkillOpt 70.5 this agent
  4. #31 ClawBio 70.2 −0.3
  5. #32 Container 69.9 −0.6

Bars show each HVTrust score; the tick marks SkillOpt’s 70.5.

Where the 70.5 comes from

HVTrust dimensions vs the Agent Skills average

70.5 / 100 · 100.0% confidence

SkillOpt Agent Skills average (385 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
10.4 / 25
2.5 above avg 7.9
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
0.6 below avg 11.4
Transparency50% declared license · 50% OSSF Scorecard
13.7 / 17
1.6 above avg 12.1
Maintenance60% last-push freshness · 40% commit activity
17.8 / 20
3.7 above avg 14.1
AdoptionLog-scaled stars · package downloads
15.1 / 20
6.1 above avg 9.0

Quick Trust Read

What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-09-30
Rank Moved
Rank rose 24 spots (#56 → #32)
2026-09-30
HVTrust Changed
HVTrust up 4.9pts (65.6 → 70.5)
2026-09-30
Activity Score Changed
Activity score up 15pts (71 → 86)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 6.1/10. Tighten the weakest checks to improve public safety evidence.
Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.
Compare with another agent Get email alerts for SkillOpt View Agent Skills Report missing data
83.9
Activity sub-score · out of 100
#30
In Agent Skills

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade B reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-10-17 20:06 UTC · Repo last pushed today

Rank Trend

2026-09-29 2026-10-17

Activity & Reach

Stars
18.5k
Forks
1.8k
Last Push
2026-10-17
today
Commits (4 wk)
28
Downloads (7d)
4,738
pypi
HN mentions (30d)
—
Open Issues
30
Rank Change
▲2
was #32

Analysis

Activity Inputs

83.9 / 100
StarsRepository reach
25.6 / 30
FreshnessLast push recency
25.0 / 25
ActivityRecent commits
18.2 / 25
CommunityFork signal
15.1 / 20

Common questions about SkillOpt

SkillOpt has a mixed signal profile. Some trust indicators are present, others are missing. Whether it is safe for your use case depends on which gaps matter to you — review the breakdown below before adopting in production.
Does SkillOpt publish package provenance?
No published build provenance is currently detected for SkillOpt. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does SkillOpt have an OpenSSF Scorecard?
SkillOpt has an OpenSSF Scorecard score of 6.1/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is SkillOpt actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does SkillOpt use?
SkillOpt ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are SkillOpt's commits signed?
56% of the last 100 commits to SkillOpt are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
medium confidence
Declared
MCP support appears present, but direct server implementation is less certain.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
3 detected
Public provider/service dependencies detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
high confidence
Declared
Declared plugin/integration surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
high confidence
Match
Published package metadata matches the tracked repo
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live
How this surface has changed

Detected changes to SkillOpt's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.

2026-09-23
Tool Surface Changed
Detected tool/plugin surface changed: none → declared
2026-09-23
Provider Added
Runtime surface grew — new detected provider dependencies: Anthropic, DeepSeek, OpenAI
2026-09-23
Mcp Status Changed
Detected MCP server support changed: none → declared
2026-09-03
Provider Added
Runtime surface grew — new detected provider dependency: DeepSeek

Maintain SkillOpt?

For maintainers

HVTrust scores SkillOpt from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
Rank 10HVTrust 4Listed 2Surface 2Grade 2Scorecard 1Delisted 1MCP 1Surface 1Score 1
2026-09-30
Rank Moved
Rank rose 24 spots (#56 → #32)
2026-09-30
HVTrust Changed
HVTrust up 4.9pts (65.6 → 70.5)
2026-09-30
Activity Score Changed
Activity score up 15pts (71 → 86)
2026-09-23
Tool Surface Changed
Detected tool/plugin surface changed: none → declared
2026-09-23
Provider Added
Runtime surface grew — new detected provider dependencies: Anthropic, DeepSeek, OpenAI
2026-09-23
Mcp Status Changed
Detected MCP server support changed: none → declared
2026-09-23
Grade Changed
Trust grade D → B
2026-09-23
Rank Moved
Rank rose 185 spots (#225 → #40)
2026-09-23
HVTrust Changed
HVTrust up 34.6pts (33.3 → 67.9)
2026-09-22
Newly Listed
First tracked at rank #225
2026-09-21
Removed From Active Tracking
Removed from active tracking
2026-09-04
Grade Changed
Trust grade D → B
2026-09-04
Rank Moved
Rank rose 179 spots (#194 → #15)
2026-09-04
HVTrust Changed
HVTrust up 25.7pts (45.4 → 71.1)
2026-09-03
Provider Added
Runtime surface grew — new detected provider dependency: DeepSeek
2026-09-01
Rank Moved
Rank dropped 15 spots (#163 → #178)
2026-08-31
Rank Moved
Rank dropped 18 spots (#145 → #163)
2026-08-30
Scorecard Added
OSSF Scorecard: 6.0/10
2026-08-30
Rank Moved
Rank rose 79 spots (#224 → #145)
2026-08-30
HVTrust Changed
HVTrust up 21.8pts (23.4 → 45.2)
2026-08-29
Rank Moved
Rank dropped 29 spots (#195 → #224)
2026-08-28
Rank Moved
Rank dropped 20 spots (#175 → #195)
2026-08-27
Rank Moved
Rank dropped 17 spots (#158 → #175)
2026-08-26
Rank Moved
Rank dropped 77 spots (#81 → #158)
2026-08-11
Newly Listed
First tracked at rank #75
GitHub → Website → PyPI: skillopt

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 70.5 Grade B
Markdown:
[![HVTrust](https://hvtracker.net/badge/skillopt.svg)](https://hvtracker.net/agents/skillopt)
HTML:
<a href="https://hvtracker.net/agents/skillopt"><img src="https://hvtracker.net/badge/skillopt.svg" alt="HVTrust"></a>

Other agents in Agent Skills

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON