Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
64 changes: 20 additions & 44 deletions .skillsaw-baseline.json
Original file line number Diff line number Diff line change
@@ -1,16 +1,8 @@
{
"version": "1",
"generated_by": "skillsaw 0.18.0",
"generated_at": "2026-08-31T00:54:48.875560+00:00",
"generated_at": "2026-08-31T17:22:24.387426+00:00",
"violations": [
{
"fingerprint": "34efa8521ae07039",
"rule_id": "agentskill-name",
"file_path": "skills/github-forge/SKILL.md",
"line": 2,
"message": "Name 'github' does not match directory name 'github-forge'",
"severity": "error"
},
{
"fingerprint": "10342080fcd47b75",
"rule_id": "agentskill-name",
Expand All @@ -20,11 +12,11 @@
"severity": "error"
},
{
"fingerprint": "a44e1496f6fe3e11",
"fingerprint": "34efa8521ae07039",
"rule_id": "agentskill-name",
"file_path": "skills/issue-labels/github/SKILL.md",
"file_path": "skills/github-forge/SKILL.md",
"line": 2,
"message": "Name 'issue-labels' does not match directory name 'github'",
"message": "Name 'github' does not match directory name 'github-forge'",
"severity": "error"
},
{
Expand All @@ -43,6 +35,14 @@
"message": "Name 'issue-labels' does not match directory name 'jira'",
"severity": "error"
},
{
"fingerprint": "a44e1496f6fe3e11",
"rule_id": "agentskill-name",
"file_path": "skills/issue-labels/github/SKILL.md",
"line": 2,
"message": "Name 'issue-labels' does not match directory name 'github'",
"severity": "error"
},
{
"fingerprint": "4aecb9c5f36aa70f",
"rule_id": "agentskill-name",
Expand All @@ -52,36 +52,21 @@
"severity": "error"
},
{
"fingerprint": "334afedb9d511d86",
"rule_id": "content-description-routing",
"fingerprint": "3841c25d67e33e68",
"rule_id": "context-budget",
"file_path": "skills/pr-risk-assessment/SKILL.md",
"line": 3,
"message": "Description does not say when to use this skill; include trigger phrasing such as 'Use when ...'",
"severity": "warning"
},
{
"fingerprint": "c0a7ffe42338cd6f",
"rule_id": "content-weak-language",
"file_path": "skills/code-implementation/SKILL.md",
"line": 161,
"message": "Weak language (vagueness): 'properly' \u2014 Remove 'properly' \u2014 describe what correct behavior looks like",
"severity": "warning"
},
{
"fingerprint": "808393ad080aa81c",
"rule_id": "content-weak-language",
"file_path": "skills/code-implementation/SKILL.md",
"line": 195,
"message": "Weak language (non-actionable): 'note that' \u2014 Restructure \u2014 state the constraint directly",
"severity": "warning"
"message": "Estimated 3,778 tokens exceeds skill warn limit of 3,000",
"severity": "warning",
"value": 3778,
"baseline_mode": "ceiling"
},
{
"fingerprint": "8aba1d160bb4c413",
"rule_id": "context-budget",
"file_path": "skills/code-implementation/SKILL.md",
"message": "Estimated 11,477 tokens exceeds skill error limit of 6,000",
"message": "Estimated 11,649 tokens exceeds skill error limit of 6,000",
"severity": "error",
"value": 11477,
"value": 11649,
"baseline_mode": "ceiling"
},
{
Expand All @@ -101,15 +86,6 @@
"severity": "error",
"value": 15709,
"baseline_mode": "ceiling"
},
{
"fingerprint": "3841c25d67e33e68",
"rule_id": "context-budget",
"file_path": "skills/pr-risk-assessment/SKILL.md",
"message": "Estimated 3,775 tokens exceeds skill warn limit of 3,000",
"severity": "warning",
"value": 3775,
"baseline_mode": "ceiling"
}
]
}
12 changes: 6 additions & 6 deletions skills/code-implementation/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -157,9 +157,9 @@ not confused with the numbered process steps below:

You should be on your feature branch with your own commits at HEAD.
If you are not — detached HEAD, or sitting on the target branch —
do not guess a branch name: follow step 4, which handles existing
branches properly (it scopes the search to this issue's number and
explains why local refs must be used rather than `origin/` ones).
do not guess a branch name: follow step 4, which scopes the
branch search to this issue's number and explains why local refs
must be used rather than `origin/` ones.
Step 4 needs the work-item identifier that step 1 would normally have
established. On a retry, use `ISSUE_NUMBER` when the source tracker is the
target forge, or derive the key from `ISSUE_URL` when it is an
Expand Down Expand Up @@ -193,9 +193,9 @@ code issue, fix the code. The feedback is redacted and truncated to
include full file contents.

If you cannot determine what failed from the feedback text, restart at
step 1 — but note that step 4 will find your existing branch, and its
guidance to treat existing work as your own and skip to verification
still applies. Do not re-implement work that is already committed.
step 1 — step 4 will find your existing branch, and its guidance to
treat existing work as your own and skip to verification still applies.
Do not re-implement work that is already committed.

### 1. Identify the issue

Expand Down
6 changes: 3 additions & 3 deletions skills/jira-components/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
---
name: jira-components
description: >-
Comment thread
rh-hemartin marked this conversation as resolved.
Discover Jira project components and recommend component assignments for
the issue being triaged. Jira-only skill using curl against the Jira Cloud
REST API. Produces component_actions in the agent result JSON.
Use when discovering Jira project components and recommending component
assignments for the issue being triaged. Jira-only skill using curl against
the Jira Cloud REST API. Produces component_actions in the agent result JSON.
---

# Jira Components
Expand Down
10 changes: 5 additions & 5 deletions skills/pr-risk-assessment/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
---
name: pr-risk-assessment
description: >-
Computes composite PR risk score from metadata, git history, and linked
issue signals. Three-tier scoring model: metadata 50%, git history 30%,
linked issue 20% (redistributed to 62/38 when no issue linked). Outputs
JSON risk object with score (1-5), level (low/moderate/elevated/high/critical),
tier signals, and rationale.
Use when computing a composite PR risk score from metadata, git history,
and linked issue signals. Three-tier scoring model: metadata 50%, git
history 30%, linked issue 20% (redistributed to 62/38 when no issue
linked). Outputs JSON risk object with score (1-5),
level (low/moderate/elevated/high/critical), tier signals, and rationale.
---

# PR Risk Assessment Scoring Model
Expand Down
Loading