leadership-change-outreach

End-to-end leadership change signal composite. Takes any set of companies, detects recent leadership changes (new VP+, C-suite hires and promotions), evaluates relevance to your product, and drafts personalized outreach. Uses Apollo People Search (free) for fast detection + Apollo Enrichment (1 credit/person) for employment history, start dates, LinkedIn URLs, and verified emails.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/outreach/composites/leadership-change-outreach/SKILL.md

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced workflow with explicit contracts and human checkpoints at every step — the process engineering is excellent. The weaknesses are a monolithic single-file structure that inlines material (title lists, filter code) belonging in bundle files, and recurring rationale/meta sections plus duplicated guidance that inflate the token cost.

Suggestions

Move the Apollo title list and the `is_valid_gtm_leader` post-filter function into references/ (e.g. references/apollo-titles.md, scripts/filter_titles.py) and reference them from Step 0/Phase 2, cutting roughly 100 lines from SKILL.md.

Trim or cut the "Why leadership changes work", "Why this beats web search", and "Key Difference from Other Signal Composites" sections — keep one line of rationale each and drop the rest.

Deduplicate the rate-limit guidance (Phase 3 and the Apollo-Specific Tips both state the 0.5s-delay/Retry-After advice) into a single place, and complete the Phase 4 lookback-check code so the detection step is copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — tables, contracts, and code earn their tokens — but there is real padding: the "Why leadership changes work" sales-psychology rationale, "Why this beats web search", and the "Key Difference from Other Signal Composites" meta-section explain context Claude could infer, and rate-limit guidance is stated twice (Phase 3 and the Tips section). Not a 2 because the bulk is dense, useful operational detail.	3 / 5
Actionability	Mostly executable: a complete `is_valid_gtm_leader` post-filter function, concrete `search_people` filter dicts, the exact `people/match` payload with `id`, explicit input/output contracts per step, and specific config schemas. Minor gaps keep it from 5: Phase 4 change detection is partial (lookback check left as a comment), the enrichment call is shown as URL+payload rather than a runnable call, and Step 5 defers entirely to another skill.	4 / 5
Workflow Clarity	Six steps (0–5) each with a stated Purpose, Input Contract, Process, Output Contract, and an explicit Human Checkpoint, plus an Execution Summary table. Error recovery is present (429 handling with Retry-After, pagination when total_entries > 100, credit accounting surfaced at the checkpoint) — matching the top anchor's sequence, validation, and feedback-loop criteria.	5 / 5
Progressive Disclosure	Good in-document structure (clear step headers, contracts, checkpoints), but the skill is a ~690-line monolith with no bundle files at all: the 28-line Apollo title list, the ~45-line post-filter function, and the full config question tables are inlined content that clearly belongs in references/ or scripts/ files. It sits between anchor 2 (separate-file content inlined) and anchor 3 (some structure, should-be-separate content inline) — structure is better than minimal, so 3.	3 / 5
	Total	15 / 20 Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description that clearly communicates what the skill does and which tools it uses, including cost transparency. Its main gap is the complete absence of a "Use when..." trigger clause, which both caps completeness and weakens auto-triggering, and a buzzwordy opening phrase.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to check for leadership changes, new executive hires, or wants outreach to newly appointed VP+/C-suite leaders at a list of companies."

Replace "End-to-end leadership change signal composite" with a plain concrete action (e.g. "Detects recent VP+ and C-suite leadership changes at target companies") to remove buzzword fluff.

Include natural trigger synonyms such as "executive changes" and "new hires" so the description matches varied user phrasing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "detects recent leadership changes (new VP+, C-suite hires and promotions)", "evaluates relevance to your product", "drafts personalized outreach" — plus named tools with costs ("Apollo People Search (free)", "Apollo Enrichment (1 credit/person)"). Not a 5 because the opener "End-to-end leadership change signal composite" is buzzword-flavored rather than a concrete action.	4 / 5
Completeness	The "what" is clear and detailed, but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere in the description — the when to use it lives only in the body. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural keywords users would say: "leadership changes", "C-suite hires", "promotions", "outreach". Missing common synonyms like "executive changes", "new hires", or "new executives" that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	A clear niche (leadership-change detection + Apollo + outreach drafting) with distinct triggers, but it overlaps the family of related outreach skills it connects to (cold-email-outreach, linkedin-outreach) — minor overlap risk, not the clean minimal-conflict case of a 5.	4 / 5
	Total	15 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (722 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/outreach/composites/leadership-change-outreach/SKILL.md
Commit: cc3e518

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.